@stephen-lord/docs 1.0.0 → 1.0.1

package/dist-docs/Agent-Skills-for-Context-Engineering/docs/blogs.md

@@ -0,0 +1,1230 @@
+---
+name: context-engineering-blogs
+description: Collection of technical blogs about context engineering, covering strategies for managing context windows in agent systems including write, select, compress, and isolate patterns.
+doc_type: blog
+source_url: No
+---
+
+Some technical blogs that I recently read and find valuable:
+
+(Context Engineering
+
+11 min read
+
+Jul 2, 2025
+
+TL;DR
+
+Agents need context to perform tasks. Context engineering is the art and science of filling the context window with just the right information at each step of an agent’s trajectory. In this post, we break down some common strategies — write, select, compress, and isolate — for context engineering by reviewing various popular agents and papers. We then explain how LangGraph is designed to support them!
+
+Also, see our video on context engineering here.
+
+General categories of context engineering
+
+Context Engineering
+
+As Andrej Karpathy puts it, LLMs are like a new kind of operating system. The LLM is like the CPU and its context window is like the RAM, serving as the model’s working memory. Just like RAM, the LLM context window has limited capacity to handle various sources of context. And just as an operating system curates what fits into a CPU’s RAM, we can think about “context engineering” playing a similar role. Karpathy summarizes this well:
+
+[Context engineering is the] ”…delicate art and science of filling the context window with just the right information for the next step.”
+
+Context types commonly used in LLM applications
+
+What are the types of context that we need to manage when building LLM applications? Context engineering as an umbrella that applies across a few different context types:
+
+Instructions – prompts, memories, few‑shot examples, tool descriptions, etc
+
+Knowledge – facts, memories, etc
+
+Tools – feedback from tool calls
+
+Context Engineering for Agents
+
+This year, interest in agents has grown tremendously as LLMs get better at reasoning and tool calling. Agents interleave LLM invocations and tool calls, often for long-running tasks. Agents interleave LLM calls and tool calls, using tool feedback to decide the next step.
+
+Agents interleave LLM calls and tool calls, using tool feedback to decide the next step
+
+However, long-running tasks and accumulating feedback from tool calls mean that agents often utilize a large number of tokens. This can cause numerous problems: it can exceed the size of the context window, balloon cost / latency, or degrade agent performance. Drew Breunig nicely outlined a number of specific ways that longer context can cause perform problems, including:
+
+Context Poisoning: When a hallucination makes it into the context
+
+Context Distraction: When the context overwhelms the training
+
+Context Confusion: When superfluous context influences the response
+
+Context Clash: When parts of the context disagree
+
+Context from tool calls accumulates over multiple agent turns
+
+With this in mind, Cognition called out the importance of context engineering:
+
+“Context engineering” … is effectively the #1 job of engineers building AI agents.
+
+Anthropic also laid it out clearly:
+
+Agents often engage in conversations spanning hundreds of turns, requiring careful context management strategies.
+
+So, how are people tackling this challenge today? We group common strategies for agent context engineering into four buckets — write, select, compress, and isolate — and give examples of each from review of some popular agent products and papers. We then explain how LangGraph is designed to support them!
+
+General categories of context engineering
+
+Write Context
+
+Writing context means saving it outside the context window to help an agent perform a task.
+
+Scratchpads
+
+When humans solve tasks, we take notes and remember things for future, related tasks. Agents are also gaining these capabilities! Note-taking via a “scratchpad” is one approach to persist information while an agent is performing a task. The idea is to save information outside of the context window so that it’s available to the agent. Anthropic’s multi-agent researcher illustrates a clear example of this:
+
+The LeadResearcher begins by thinking through the approach and saving its plan to Memory to persist the context, since if the context window exceeds 200,000 tokens it will be truncated and it is important to retain the plan.
+
+Scratchpads can be implemented in a few different ways. They can be a tool call that simply writes to a file. They can also be a field in a runtime state object that persists during the session. In either case, scratchpads let agents save useful information to help them accomplish a task.
+
+Memories
+
+Scratchpads help agents solve a task within a given session (or thread), but sometimes agents benefit from remembering things across many sessions! Reflexion introduced the idea of reflection following each agent turn and re-using these self-generated memories. Generative Agents created memories synthesized periodically from collections of past agent feedback.
+
+An LLM can be used to update or create memories
+
+These concepts made their way into popular products like ChatGPT, Cursor, and Windsurf, which all have mechanisms to auto-generate long-term memories that can persist across sessions based on user-agent interactions.
+
+Select Context
+
+Selecting context means pulling it into the context window to help an agent perform a task.
+
+Scratchpad
+
+The mechanism for selecting context from a scratchpad depends upon how the scratchpad is implemented. If it’s a tool, then an agent can simply read it by making a tool call. If it’s part of the agent’s runtime state, then the developer can choose what parts of state to expose to an agent each step. This provides a fine-grained level of control for exposing scratchpad context to the LLM at later turns.
+
+Memories
+
+If agents have the ability to save memories, they also need the ability to select memories relevant to the task they are performing. This can be useful for a few reasons. Agents might select few-shot examples (episodic memories) for examples of desired behavior, instructions (procedural memories) to steer behavior, or facts (semantic memories) for task-relevant context.
+
+One challenge is ensuring that relevant memories are selected. Some popular agents simply use a narrow set of files that are always pulled into context. For example, many code agent use specific files to save instructions (”procedural” memories) or, in some cases, examples (”episodic” memories). Claude Code uses CLAUDE.md. Cursor and Windsurf use rules files.
+
+But, if an agent is storing a larger collection of facts and / or relationships (e.g., semantic memories), selection is harder. ChatGPT is a good example of a popular product that stores and selects from a large collection of user-specific memories.
+
+Embeddings and / or knowledge graphs for memory indexing are commonly used to assist with selection. Still, memory selection is challenging. At the AIEngineer World’s Fair, Simon Willison shared an example of selection gone wrong: ChatGPT fetched his location from memories and unexpectedly injected it into a requested image. This type of unexpected or undesired memory retrieval can make some users feel like the context window “no longer belongs to them”!
+
+Tools
+
+Agents use tools, but can become overloaded if they are provided with too many. This is often because the tool descriptions overlap, causing model confusion about which tool to use. One approach is to apply RAG (retrieval augmented generation) to tool descriptions in order to fetch only the most relevant tools for a task. Some recent papers have shown that this improve tool selection accuracy by 3-fold.
+
+Knowledge
+
+RAG is a rich topic and it can be a central context engineering challenge. Code agents are some of the best examples of RAG in large-scale production. Varun from Windsurf captures some of these challenges well:
+
+Indexing code ≠ context retrieval … [We are doing indexing & embedding search … [with] AST parsing code and chunking along semantically meaningful boundaries … embedding search becomes unreliable as a retrieval heuristic as the size of the codebase grows … we must rely on a combination of techniques like grep/file search, knowledge graph based retrieval, and … a re-ranking step where [context] is ranked in order of relevance.
+
+Compressing Context
+
+Compressing context involves retaining only the tokens required to perform a task.
+
+Context Summarization
+
+Agent interactions can span hundreds of turns and use token-heavy tool calls. Summarization is one common way to manage these challenges. If you’ve used Claude Code, you’ve seen this in action. Claude Code runs “auto-compact” after you exceed 95% of the context window and it will summarize the full trajectory of user-agent interactions. This type of compression across an agent trajectory can use various strategies such as recursive or hierarchical summarization.
+
+A few places where summarization can be applied
+
+It can also be useful to add summarization at specific points in an agent’s design. For example, it can be used to post-process certain tool calls (e.g., token-heavy search tools). As a second example, Cognition mentioned summarization at agent-agent boundaries to reduce tokens during knowledge hand-off. Summarization can be a challenge if specific events or decisions need to be captured. Cognition uses a fine-tuned model for this, which underscores how much work can go into this step.
+
+Context Trimming
+
+Whereas summarization typically uses an LLM to distill the most relevant pieces of context, trimming can often filter or, as Drew Breunig points out, “prune” context. This can use hard-coded heuristics like removing older messages from a list. Drew also mentions Provence, a trained context pruner for Question-Answering.
+
+Isolating Context
+
+Isolating context involves splitting it up to help an agent perform a task.
+
+Multi-agent
+
+One of the most popular ways to isolate context is to split it across sub-agents. A motivation for the OpenAI Swarm library was separation of concerns, where a team of agents can handle specific sub-tasks. Each agent has a specific set of tools, instructions, and its own context window.
+
+Split context across multiple agents
+
+Anthropic’s multi-agent researcher makes a case for this: many agents with isolated contexts outperformed single-agent, largely because each subagent context window can be allocated to a more narrow sub-task. As the blog said:
+
+[Subagents operate] in parallel with their own context windows, exploring different aspects of the question simultaneously.
+
+Of course, the challenges with multi-agent include token use (e.g., up to 15× more tokens than chat as reported by Anthropic), the need for careful prompt engineering to plan sub-agent work, and coordination of sub-agents.
+
+Context Isolation with Environments
+
+HuggingFace’s deep researcher shows another interesting example of context isolation. Most agents use tool calling APIs, which return JSON objects (tool arguments) that can be passed to tools (e.g., a search API) to get tool feedback (e.g., search results). HuggingFace uses a CodeAgent, which outputs that contains the desired tool calls. The code then runs in a sandbox. Selected context (e.g., return values) from the tool calls is then passed back to the LLM.
+
+Sandboxes can isolate context from the LLM.
+
+This allows context to be isolated from the LLM in the environment. Hugging Face noted that this is a great way to isolate token-heavy objects in particular:
+
+[Code Agents allow for] a better handling of state … Need to store this image / audio / other for later use? No problem, just assign it as a variable in your state and you [use it later].
+
+State
+
+It’s worth calling out that an agent’s runtime state object can also be a great way to isolate context. This can serve the same purpose as sandboxing. A state object can be designed with a schema that has fields that context can be written to. One field of the schema (e.g., messages) can be exposed to the LLM at each turn of the agent, but the schema can isolate information in other fields for more selective use.
+
+Context Engineering with LangSmith / LangGraph
+
+So, how can you apply these ideas? Before you start, there are two foundational pieces that are helpful. First, ensure that you have a way to look at your data and track token-usage across your agent. This helps inform where best to apply effort context engineering. LangSmith is well-suited for agent tracing / observability, and offers a great way to do this. Second, be sure you have a simple way to test whether context engineering hurts or improve agent performance. LangSmith enables agent evaluation to test the impact of any context engineering effort.
+
+Write context
+
+LangGraph was designed with both thread-scoped (short-term) and long-term memory. Short-term memory uses checkpointing to persist agent state across all steps of an agent. This is extremely useful as a “scratchpad”, allowing you to write information to state and fetch it at any step in your agent trajectory.
+
+LangGraph’s long-term memory lets you to persist context across many sessions with your agent. It is flexible, allowing you to save small sets of files (e.g., a user profile or rules) or larger collections of memories. In addition, LangMem provides a broad set of useful abstractions to aid with LangGraph memory management.
+
+Select context
+
+Within each node (step) of a LangGraph agent, you can fetch state. This give you fine-grained control over what context you present to the LLM at each agent step.
+
+In addition, LangGraph’s long-term memory is accessible within each node and supports various types of retrieval (e.g., fetching files as well as embedding-based retrieval on a memory collection). For an overview of long-term memory, see our Deeplearning.ai course. And for an entry point to memory applied to a specific agent, see our Ambient Agents course. This shows how to use LangGraph memory in a long-running agent that can manage your email and learn from your feedback.
+
+Email agent with user feedback and long-term memory
+
+For tool selection, the LangGraph Bigtool library is a great way to apply semantic search over tool descriptions. This helps select the most relevant tools for a task when working with a large collection of tools. Finally, we have several tutorials and videos that show how to use various types of RAG with LangGraph.
+
+Compressing context
+
+Because LangGraph is a low-level orchestration framework, you lay out your agent as a set of nodes, define the logic within each one, and define an state object that is passed between them. This control offers several ways to compress context.
+
+One common approach is to use a message list as your agent state and summarize or trim it periodically using a few built-in utilities. However, you can also add logic to post-process tool calls or work phases of your agent in a few different ways. You can add summarization nodes at specific points or also add summarization logic to your tool calling node in order to compress the output of specific tool calls.
+
+Isolating context
+
+LangGraph is designed around a state object, allowing you to specify a state schema and access state at each agent step. For example, you can store context from tool calls in certain fields in state, isolating them from the LLM until that context is required. In addition to state, LangGraph supports use of sandboxes for context isolation. See this repo for an example LangGraph agent that uses an E2B sandbox for tool calls. See this video for an example of sandboxing using Pyodide where state can be persisted. LangGraph also has a lot of support for building multi-agent architecture, such as the supervisor and swarm libraries. You can see these videos for more detail on using multi-agent with LangGraph.
+
+Conclusion
+
+Context engineering is becoming a craft that agents builders should aim to master. Here, we covered a few common patterns seen across many popular agents today:
+
+Writing context - saving it outside the context window to help an agent perform a task.
+
+Selecting context - pulling it into the context window to help an agent perform a task.
+
+Compressing context - retaining only the tokens required to perform a task.
+
+Isolating context - splitting it up to help an agent perform a task.
+
+LangGraph makes it easy to implement each of them and LangSmith provides an easy way to test your agent and track context usage. Together, LangGraph and LangGraph enable a virtuous feedback loop for identifying the best opportunity to apply context engineering, implementing it, testing it, and repeating.
+
+---------
+
+Context Engineering in Manus
+
+Oct 15, 2025
+
+Lance Martin
+
+Why Context Engineering
+
+Earlier this week, I had a webinar with Manus co-founder and CSO Yichao “Peak” Ji. You can see the video here, my slides here, and Peak’s slides here. Below are my notes.
+
+Anthropic defines agents as systems where LLMs direct their own processes and tool usage, maintaining control over how they accomplish tasks. In short, it’s an LLM calling tools in a loop.
+
+Manus is one of the most popular general-purpose consumer agents. The typical Manus task uses 50 tool calls. Without context engineering, these tool call results would accumulate in the LLM context window. As the context window fills, many have observed that LLM performance degrades.
+
+For example, Chroma has a great study on context rot and Anthropic has explained how growing context depletes an LLM’s attention budget. So, it’s important to carefully manage what goes into the LLM’s context window when building agents. Karpathy laid this out clearly:
+
+Context engineering is the delicate art and science of filling the context window with just the right information for the next step (in an agent’s trajectory)
+
+Context Engineering Approaches
+
+Each Manus session uses a dedicated cloud-based virtual machine, giving the agent a virtual computer with a filesystem, tools to navigate it, and the ability to execute commands (e.g., provided utilities and standard shell commands) in that sandbox environment.
+
+In this sandbox, Manus uses three primary strategies for context engineering, which align with approaches Anthropic covers here and I’ve seen in across many projects:
+
+Reduce Context
+
+Offload Context
+
+Isolate Context
+
+Context Reduction
+
+Tool calls in Manus have a “full” and “compact” representation. The full version contains the raw content from tool invocation (e.g., a complete search tool result), which is stored in the sandbox (e.g., filesystem). The compact version stores a reference to the full result (e.g., a file path).
+
+Manus applies compaction to older (“stale”) tool results. This just means swapping out the full tool result for the compact version. This allows the agent to still fetch the full result if ever needed, but saves tokens by removing “stale” results that the agent has already used to make decisions.
+
+Newer tool results remain in full to guide the agent’s next decision. This seems to be a generally useful strategy for context reduction, and I notice that it’s similar to Anthropic’s context editing feature:
+
+Context editing automatically clears stale tool calls and results from within the context window when approaching token limits. As your agent executes tasks and accumulates tool results, context editing removes stale content while preserving the conversation flow, effectively extending how long agents can run without manual intervention.
+
+When compaction reaches diminishing returns (see figure below), Manus applies summarization to the trajectory. Summaries are generated using full tool results and Manus uses a schema to define the summary fields. This creates a consistent summary object for any agent trajectory.
+
+Context Isolation
+
+Manus takes a pragmatic approach to multi-agent, avoiding anthropomorphized divisions of labor. While humans organize by role (designer, engineer, project manager) due to cognitive limitations, LLMs don’t necessarily share these same constraints.
+
+With this in mind, the primary goal of sub-agents in Manus is to isolate context. For example, if there’s a task to be done, Manus will assign that task to a sub-agent with its own context window.
+
+Manus uses multi-agent with a planner that assigns tasks, a knowledge manager that reviews conversations and determines what should be saved in the filesystem, and an executor sub-agent that performs tasks assigned by the planner.
+
+Manus initially used a todo.md for task planning, but found that roughly one-third of all actions were spent updating the todo list, wasting valuable tokens. They shifted to a dedicated planner agent that calls executor sub-agents to perform tasks.
+
+In a recent podcast, Erik Schluntz (multi-agent research at Anthropic) mentioned that they similarly design multi-agent systems with a planner to assign tasks and use function calling as the communication protocol to initiate sub-agents. A central challenge raised by Erik as well as Walden Yan (Cognition) is context sharing between planner and sub-agents.
+
+Manus addresses this in two ways. For simple tasks (e.g., a discrete task where the planner only needs the output of the sub-agent), the planner simply creates instructions and passes them to the sub-agent via the function call. This resembles Claude Code’s task tool.
+
+For more complex tasks (e.g., the sub-agent needs to write to files that the planner also uses), the planner shares its full context with the sub-agent. The sub-agent still has its own action space (tools) and instructions, but receives the full context that the planner also has access to.
+
+In both cases, the planner defines the sub-agent’s output schema. Sub-agents have a submit results tool to populate this schema before returning results to the planner and Manus uses constrained decoding to ensure output adheres to the defined schema.
+
+Context Offloading
+
+Tools Definitions
+
+We often want agents that can perform a wide range of actions. We can, of course, bind a large collection of tools to the LLM and provide detailed instructions on how to use all of them. But, tool descriptions use valuable tokens and many (often overlapping or ambiguous) tools can cause model confusion.
+
+A trend I’m seeing is that agents use a small set of general tools that give the agent access to a computer. For example, with only a Bash tool and a few tools to access a filesystem, an agent can perform a wide range of actions!
+
+Manus thinks about this as a layered action space with function/tool calling and its virtual computer sandbox. Peak mentioned that Manus uses a small set (< 20) of atomic functions; this includes things like a Bash tool, tools to manage the filesystem, and a code execution tool.
+
+Rather than bloating the function calling layer, Manus offloads most actions to the sandbox layer. Manus can execute many utilities directly in the sandbox with its Bash tool and MCP tools are exposed through a CLI that the agent can also execute using the Bash tool.
+
+Claude’s skills feature uses a similar idea:skills are stored in the filesystem, not as bound tools, and Claude only needs a few simple function calls (Bash, file system) to progressively discover and use them.
+
+Progressive disclosure is the core design principle that makes Agent Skills flexible and scalable. Like a well-organized manual that starts with a table of contents, then specific chapters, and finally a detailed appendix, skills let Claude load information only as needed … agents with a filesystem and code execution tools don’t need to read the entirety of a skill into their context window when working on a particular task.
+
+Tool Results
+
+Because Manus has access to a filesystem, it can also offload context (e.g., tool results). As explained above, this is central for context reduction; tool results are offloaded to the filesystem in order to produce the compact version and this is used to prune stale tokens from the agent’s context window. Similar to Claude Code, Manus uses basic utilities (e.g., glob and grep) to search the filesystem without the need for indexing (e.g., vectorstores).
+
+Model Choice
+
+Rather than committing to a single model, Manus uses task-level routing: it might use Claude for coding, Gemini for multi-modal tasks, or OpenAI for math and reasoning. Broadly, Manus’s approach to model selection is driven by cost considerations, with KV cache efficiency playing a central role.
+
+Manus uses caching (e.g., for system instructions, older tool results, etc) to reduce both cost and latency across many agent turns. Peak mentioned that distributed KV cache infrastructure is challenging to implement with open source models, but is well-supported by frontier providers. This caching support can make frontier models cheaper for certain (agent) use-cases in practice.
+
+Build with the Bitter Lesson in Mind
+
+We closed the discussion talking about the Bitter Lesson. I’ve been interested in its implications for AI engineering. Boris Cherny (creator of Claude Code) mentioned that The Bitter Lesson influenced his decision to keep Claude Code unopinionated, making it easier to adapt to model improvements.
+
+Building on constantly improving models means accepting constant change. Peak mentioned that Manus has been refactored five times since their launch in March!
+
+In addition, Peak warned that the agent’s harness can limit performance as models advance; this is exactly the challenge called out by the Bitter Lesson. We add structure to improve performance at a point in time, but this structure can limit performance as compute (models) grows.
+
+To guard against this, Peak suggested running agent evaluations across varying model strengths. If performance doesn’t improve with stronger models, your harness may be hobbling the agent. This can help test whether your harness is “future proof”.
+
+Hyung Won Chung’s (OpenAI/MSL) talk on this topic further emphasizes the need to consistently re-evaluate structure (e.g., your harness / assumptions) as models improve.
+
+Add structures needed for the given level of compute and data available. Remove them later, because these shortcuts will bottleneck further improvement.
+
+Conclusions
+
+Giving agents access to a computer (e.g., filesystem, terminal, utilities) is a common pattern we see across many agents, including Manus. It enables a few context engineering strategies:
+
+1. Offload Context
+
+Store tool results externally: Save full tool results to the filesystem (not in context) and access on demand with utilities like glob and grep
+
+Push actions to the sandbox: Use a small set of function calls (Bash, filesystem access) that can execute many utilities in the sandbox rather than binding every utility as a tool
+
+2. Reduce Context
+
+Compact stale results: Replace older tool results with references (e.g., file paths) as context fills; keep recent results in full to guide the next decision
+
+Summarize when needed: Once compaction reaches diminishing returns, apply schema-based summarization to the full trajectory
+
+3. Isolate Context
+
+Use sub-agents for discrete tasks: Assign tasks to sub-agents with their own context windows, primarily to isolate context (not to divide labor by role)
+
+Share context deliberately: Pass only instructions for simple tasks; pass full context (e.g., trajectory and shared filesystem) for complex tasks where sub-agents need more context
+
+A final consideration is to ensure your harness is not limiting performance as models improve (e.g., be “Bitter Lesson-pilled”). Test across model strengths to verify this. Simple, unopinionated designs often adapt better to model improvements. Finally, don’t be afraid to re-build your agent as models improve (Manus refactored 5 times since March)!
+
+-----
+
+Context Engineering for AI Agents: Lessons from Building Manus
+
+2025/7/18 --Yichao 'Peak' Ji
+
+At the very beginning of the  project, my team and I faced a key decision: should we train an end-to-end agentic model using open-source foundations, or build an agent on top of the  abilities of frontier models?
+
+Back in my first decade in NLP, we didn't have the luxury of that choice. In the distant days of  (yes, it's been seven years), models had to be fine-tuned—and evaluated—before they could transfer to a new task. That process often took weeks per iteration, even though the models were tiny compared to today's LLMs. For fast-moving applications, especially pre–PMF, such slow feedback loops are a deal-breaker. That was a bitter lesson from my last startup, where I trained models from scratch for  and semantic search. Then came  and , and my in-house models became irrelevant overnight. Ironically, those same models marked the beginning of in-context learning—and a whole new path forward.
+
+That hard-earned lesson made the choice clear: Manus would bet on context engineering. This allows us to ship improvements in hours instead of weeks, and kept our product orthogonal to the underlying models: If model progress is the rising tide, we want Manus to be the boat, not the pillar stuck to the seabed.
+
+Still, context engineering turned out to be anything but straightforward. It's an experimental science—and we've rebuilt our agent framework four times, each time after discovering a better way to shape context. We affectionately refer to this manual process of architecture searching, prompt fiddling, and empirical guesswork as "Stochastic Graduate Descent". It's not elegant, but it works.
+
+This post shares the local optima we arrived at through our own "SGD". If you're building your own AI agent, I hope these principles help you converge faster.
+
+Design Around the KV-Cache
+
+If I had to choose just one metric, I'd argue that the KV-cache hit rate is the single most important metric for a production-stage AI agent. It directly affects both latency and cost. To understand why, let's look at how  operates:
+
+After receiving a user input, the agent proceeds through a chain of tool uses to complete the task. In each iteration, the model selects an action from a predefined action space based on the current context. That action is then executed in the environment (e.g., Manus's virtual machine sandbox) to produce an observation. The action and observation are appended to the context, forming the input for the next iteration. This loop continues until the task is complete.
+
+As you can imagine, the context grows with every step, while the output—usually a structured function call—remains relatively short. This makes the ratio between prefilling and decoding highly skewed in agents compared to chatbots. In Manus, for example, the average input-to-output token ratio is around 100:1.
+
+Fortunately, contexts with identical prefixes can take advantage of , which drastically reduces time-to-first-token (TTFT) and inference cost—whether you're using a self-hosted model or calling an inference API. And we're not talking about small savings: with Claude Sonnet, for instance, cached input tokens cost 0.30 USD/MTok, while uncached ones cost 3 USD/MTok—a 10x difference.
+
+From a context engineering perspective, improving KV-cache hit rate involves a few key practices:
+
+Keep your prompt prefix stable. Due to the  nature of LLMs, even a single-token difference can invalidate the cache from that token onward. A common mistake is including a timestamp—especially one precise to the second—at the beginning of the system prompt. Sure, it lets the model tell you the current time, but it also kills your cache hit rate.
+
+Make your context append-only. Avoid modifying previous actions or observations. Ensure your serialization is deterministic. Many programming languages and libraries don't guarantee stable key ordering when serializing JSON objects, which can silently break the cache.
+
+Mark cache breakpoints explicitly when needed. Some model providers or inference frameworks don't support automatic incremental prefix caching, and instead require manual insertion of cache breakpoints in the context. When assigning these, account for potential cache expiration and at minimum, ensure the breakpoint includes the end of the system prompt.
+
+Additionally, if you're self-hosting models using frameworks like , make sure  is enabled, and that you're using techniques like session IDs to route requests consistently across distributed workers.
+
+Mask, Don't Remove
+
+As your agent takes on more capabilities, its action space naturally grows more complex—in plain terms, the number of tools explodes. The recent popularity of  only adds fuel to the fire. If you allow user-configurable tools, trust me: someone will inevitably plug hundreds of mysterious tools into your carefully curated action space. As a result, the model is more likely to select the wrong action or take an inefficient path. In short, your heavily armed agent gets dumber.
+
+A natural reaction is to design a dynamic action space—perhaps loading tools on demand using something -like. We tried that in Manus too. But our experiments suggest a clear rule: unless absolutely necessary, avoid dynamically adding or removing tools mid-iteration. There are two main reasons for this:
+
+In most LLMs, tool definitions live near the front of the context after serialization, typically before or after the system prompt. So any change will invalidate the KV-cache for all subsequent actions and observations.
+
+When previous actions and observations still refer to tools that are no longer defined in the current context, the model gets confused. Without , this often leads to schema violations or hallucinated actions.
+
+To solve this while still improving action selection, Manus uses a context-aware  to manage tool availability. Rather than removing tools, it masks the token logits during decoding to prevent (or enforce) the selection of certain actions based on the current context.
+
+In practice, most model providers and inference frameworks support some form of response prefill, which allows you to constrain the action space without modifying the tool definitions. There are generally three modes of function calling (we'll use the  from NousResearch as an example):
+
+Auto – The model may choose to call a function or not. Implemented by prefilling only the reply prefix: <|im_start|>assistant
+
+Required – The model must call a function, but the choice is unconstrained. Implemented by prefilling up to tool call token: <|im_start|>assistant<tool_call>
+
+Specified – The model must call a function from a specific subset. Implemented by prefilling up to the beginning of the function name: <|im_start|>assistant<tool_call>{"name": “browser_
+
+Using this, we constrain action selection by masking token logits directly. For example, when the user provides a new input, Manus must reply immediately instead of taking an action. We've also deliberately designed action names with consistent prefixes—e.g., all browser-related tools start with browser_, and command-line tools with shell_. This allows us to easily enforce that the agent only chooses from a certain group of tools at a given state without using stateful logits processors.
+
+These designs help ensure that the Manus agent loop remains stable—even under a model-driven architecture.
+
+Use the File System as Context
+
+Modern frontier LLMs now offer context windows of 128K tokens or more. But in real-world agentic scenarios, that's often not enough, and sometimes even a liability. There are three common pain points:
+
+Observations can be huge, especially when agents interact with unstructured data like web pages or PDFs. It's easy to blow past the context limit.
+
+Model performance tends to degrade beyond a certain context length, even if the window technically supports it.
+
+Long inputs are expensive, even with prefix caching. You're still paying to transmit and prefill every token.
+
+To deal with this, many agent systems implement context truncation or compression strategies. But overly aggressive compression inevitably leads to information loss. The problem is fundamental: an agent, by nature, must predict the next action based on all prior state—and you can't reliably predict which observation might become critical ten steps later. From a logical standpoint, any irreversible compression carries risk.
+
+That's why we treat the file system as the ultimate context in Manus: unlimited in size, persistent by nature, and directly operable by the agent itself. The model learns to write to and read from files on demand—using the file system not just as storage, but as structured, externalized memory.
+
+Our compression strategies are always designed to be restorable. For instance, the content of a web page can be dropped from the context as long as the URL is preserved, and a document's contents can be omitted if its path remains available in the sandbox. This allows Manus to shrink context length without permanently losing information.
+
+While developing this feature, I found myself imagining what it would take for a State Space Model (SSM) to work effectively in an agentic setting. Unlike Transformers, SSMs lack full attention and struggle with long-range backward dependencies. But if they could master file-based memory—externalizing long-term state instead of holding it in context—then their speed and efficiency might unlock a new class of agents. Agentic SSMs could be the real successors to .
+
+Manipulate Attention Through Recitation
+
+If you've worked with Manus, you've probably noticed something curious: when handling complex tasks, it tends to create a todo.md file—and update it step-by-step as the task progresses, checking off completed items.
+
+That's not just cute behavior—it's a deliberate mechanism to manipulate attention.
+
+A typical task in Manus requires around 50 tool calls on average. That's a long loop—and since Manus relies on LLMs for decision-making, it's vulnerable to drifting off-topic or forgetting earlier goals, especially in long contexts or complicated tasks.
+
+By constantly rewriting the todo list, Manus is reciting its objectives into the end of the context. This pushes the global plan into the model's recent attention span, avoiding "lost-in-the-middle" issues and reducing goal misalignment. In effect, it's using natural language to bias its own focus toward the task objective—without needing special architectural changes.
+
+Keep the Wrong Stuff In
+
+Agents make mistakes. That's not a bug—it's reality. Language models hallucinate, environments return errors, external tools misbehave, and unexpected edge cases show up all the time. In multi-step tasks, failure is not the exception; it's part of the loop.
+
+And yet, a common impulse is to hide these errors: clean up the trace, retry the action, or reset the model's state and leave it to the magical "". That feels safer, more controlled. But it comes at a cost: Erasing failure removes evidence. And without evidence, the model can't adapt.
+
+In our experience, one of the most effective ways to improve agent behavior is deceptively simple: leave the wrong turns in the context. When the model sees a failed action—and the resulting observation or stack trace—it implicitly updates its internal beliefs. This shifts its prior away from similar actions, reducing the chance of repeating the same mistake. In fact, we believe error recovery is one of the clearest indicators of true agentic behavior. Yet it's still underrepresented in most academic work and public benchmarks, which often focus on task success under ideal conditions.
+
+Don't Get Few-Shotted
+
+ is a common technique for improving LLM outputs. But in agent systems, it can backfire in subtle ways.
+
+Language models are excellent mimics; they imitate the pattern of behavior in the context. If your context is full of similar past action-observation pairs, the model will tend to follow that pattern, even when it's no longer optimal.
+
+This can be dangerous in tasks that involve repetitive decisions or actions. For example, when using Manus to help review a batch of 20 resumes, the agent often falls into a rhythm—repeating similar actions simply because that's what it sees in the context. This leads to drift, overgeneralization, or sometimes hallucination.
+
+The fix is to increase diversity. Manus introduces small amounts of structured variation in actions and observations—different serialization templates, alternate phrasing, minor noise in order or formatting. This controlled randomness helps break the pattern and tweaks the model's attention. In other words, don't few-shot yourself into a rut. The more uniform your context, the more brittle your agent becomes.
+
+Conclusion
+
+Context engineering is still an emerging science—but for agent systems, it's already essential. Models may be getting stronger, faster, and cheaper, but no amount of raw capability replaces the need for memory, environment, and feedback. How you shape the context ultimately defines how your agent behaves: how fast it runs, how well it recovers, and how far it scales.
+
+At Manus, we've learned these lessons through repeated rewrites, dead ends, and real-world testing across millions of users. None of what we've shared here is universal truth—but these are the patterns that worked for us. If they help you avoid even one painful iteration, then this post did its job.
+
+The agentic future will be built one context at a time. Engineer them well.
+
+------
+
+Wide Research: Beyond the Context Window
+
+The promise of AI-driven research has always been compelling: delegate the tedious work of information gathering and synthesis to an intelligent system, freeing up human cognition for higher-order analysis and decision-making. Yet, anyone who has pushed these systems on non-trivial use cases has run into a frustrating reality: by the eighth or ninth item in a multi-subject research task, the AI starts fabricating.
+
+Not just simplifying. Not just summarizing more concisely. Fabricating.
+
+This isn't a prompt engineering problem. It's not a model capability problem. It is an architectural constraint that has quietly limited the utility of AI research tools since their inception. And it's the constraint that Wide Research is designed to overcome.
+
+The Context Window: A Fundamental Bottleneck
+
+Every large language model operates within a context window, a finite memory buffer that limits the amount of information the model can actively process at any given moment. Modern models have pushed this boundary impressively: from 4K tokens to 32K, 128K, and even 1M tokens in recent versions.
+
+Yet the problem persists.
+
+When you ask an AI to research multiple entities-say, fifty companies, thirty research papers, or twenty competing products-the context window fills up rapidly. It's not just the raw information about each entity, but also:
+
+The original task specification and requirements
+
+The structural template for consistent output formatting
+
+Intermediate reasoning and analysis for each item
+
+Cross-referencing and comparative notes
+
+The cumulative context of all preceding items
+
+By the time the model reaches the eighth or ninth item, the context window is under immense strain. The model faces an impossible choice: fail explicitly, or start cutting corners.
+
+It always chooses the latter.
+
+The Fabrication Threshold
+
+Here's what happens in practice:
+
+Items 1-5: The model performs genuine research. It retrieves information, cross-references sources, and produces detailed, accurate analysis.
+
+Items 6-8: The quality begins to subtly degrade. Descriptions become slightly more generic. The model starts relying more on prior patterns than fresh research.
+
+Items 9+: The model enters fabrication mode. Unable to maintain the cognitive load of thorough research while managing an overflowing context, it begins generating plausible-sounding content based on statistical patterns, not actual investigation.
+
+These fabrications are sophisticated. They sound authoritative. They follow the established format perfectly. They are often grammatically flawless and stylistically consistent with the earlier, legitimate entries.
+
+They are also frequently wrong.
+
+A competitor analysis might attribute features to companies that don't offer them. A literature review might cite papers with fabricated findings. A product comparison might invent pricing tiers or specifications.
+
+The insidious part is that these fabrications are difficult to detect without manual verification—which defeats the entire purpose of automated research.
+
+Why Bigger Context Windows Can't Fix This
+
+The intuitive response is to simply expand the context window. If 32K tokens aren't enough, use 128K. If that's not enough, push to 200K or beyond.
+
+This approach misunderstands the problem.
+
+First, context decay is not binary. A model does not maintain perfect recall across its entire context window. Studies have shown that retrieval accuracy degrades with distance from the current position—the "lost in the middle" phenomenon. Information at the beginning and end of the context is recalled more reliably than information in the middle.
+
+Second, the processing cost grows disproportionately. The cost to process a 400K token context isn't just double the cost of 200K—it increases exponentially in both time and computing resources. This makes massive-context processing economically impractical for many use cases.
+
+Third, the problem is cognitive load. Even with an infinite context, asking a single model to maintain consistent quality across dozens of independent research tasks creates a cognitive bottleneck. The model must constantly switch context between items, maintain a comparative framework, and ensure stylistic consistency—all while performing the core research task.
+
+Fourth, context length pressure. The model’s “patience” is, to some extent, determined by the length distribution of samples in its training data. However, the post-training data mixture of current language models is still dominated by relatively short trajectories designed for chatbot-style interactions. As a result, when the length of an assistant message’s content exceeds a certain threshold, the model naturally experiences a kind of context length pressure, prompting it to hasten toward summarizing or to resort to incomplete expression forms such as bullet points.
+
+The context window is a constraint, yes. But it's a symptom of a deeper architectural limitation: the single-processor, sequential paradigm.
+
+The Architectural Shift: Parallel Processing
+
+Wide Research represents a fundamental rethinking of how an AI system should approach large-scale research tasks. Instead of asking one processor to handle n items sequentially, we deploy n parallel sub-agents to process n items simultaneously.
+
+The Wide Research Architecture
+
+When you launch a Wide Research task, the system operates as follows:
+
+1. Intelligent Decomposition
+
+The main controller analyzes your request and breaks it down into independent, parallelizable sub-tasks. This involves understanding the task structure, identifying dependencies, and creating coherent sub-specifications.
+
+2. Sub-agent Delegation
+
+For each sub-task, the system spins up a dedicated sub-agent. Crucially, these are not lightweight processes—they are full-featured Manus instances, each with:
+
+A complete virtual machine environment
+
+Access to the full tool library (search, browsing, code execution, file handling)
+
+An independent internet connection
+
+A fresh, empty context window
+
+3. Parallel Execution
+
+All sub-agents execute simultaneously. Each one focuses exclusively on its assigned item, performing the same depth of research and analysis it would for a single-item task.
+
+4. Centralized Coordination
+
+The main controller maintains oversight, collecting results as the sub-agents complete their jobs. Importantly, the sub-agents do not communicate with each other, all coordination flows through the main controller. This prevents context pollution and maintains independence.
+
+5. Synthesis and Integration
+
+Once all sub-agents have reported back, the main controller synthesizes the results into a single, coherent, and comprehensive report. This synthesis step leverages the full context capacity of the main controller, as it is not burdened with the original research effort.
+
+Why This Changes Everything
+
+Consistent Quality at Scale
+
+Every item gets the same treatment. The 50th item is researched just as thoroughly as the first. There is no degradation curve, no fabrication threshold, and no quality cliff.
+
+True Horizontal Scalability
+
+Need to analyze 10 items? The system deploys 10 sub-agents. Need to analyze 500? It deploys 500. The architecture scales linearly with the size of the task, not exponentially like context-based approaches.
+
+Significant Speed-Up
+
+Because the sub-agents operate in parallel, the real-world time required to analyze 50 items is roughly the same as the time to analyze 5. The bottleneck shifts from sequential processing time to synthesis time—a much smaller component of the overall task.
+
+Reduced Hallucination Rate
+
+Each sub-agent operates within its cognitive comfort zone. With a fresh context and a single, focused task, there is no pressure to fabricate. The sub-agent can perform genuine research, verify facts, and maintain accuracy.
+
+Independence and Reliability
+
+Because the sub-agents do not share context, an error or hallucination in one sub-agent's job does not propagate to the others. Each analysis stands on its own, reducing systemic risk.
+
+Beyond the Single-Processor Paradigm
+
+Wide Research is more than a feature—it represents a fundamental shift away from the single-processor paradigm and toward an orchestrated, parallel architecture. The future of AI systems lies not in ever-larger context windows, but in intelligent task decomposition and parallel execution.
+
+We are moving from the era of the "AI assistant" to the era of the "AI workforce."
+
+When to use Wide Research: Any task involving multiple, similar items that require consistent analysiscompetitive research, literature reviews, bulk processing, multi-asset generation.
+
+When not to use: Deeply sequential tasks where each step heavily depends on the prior result, or small tasks (fewer than 10 items) where single-processor handling is more cost-effective.
+
+--------
+
+How we built our multi-agent research system
+
+Published Jun 13, 2025
+
+Our Research feature uses multiple Claude agents to explore complex topics more effectively. We share the engineering challenges and the lessons we learned from building this system.
+
+Claude now has Research capabilities that allow it to search across the web, Google Workspace, and any integrations to accomplish complex tasks.
+
+The journey of this multi-agent system from prototype to production taught us critical lessons about system architecture, tool design, and prompt engineering. A multi-agent system consists of multiple agents (LLMs autonomously using tools in a loop) working together. Our Research feature involves an agent that plans a research process based on user queries, and then uses tools to create parallel agents that search for information simultaneously. Systems with multiple agents introduce new challenges in agent coordination, evaluation, and reliability.
+
+This post breaks down the principles that worked for us—we hope you'll find them useful to apply when building your own multi-agent systems.
+
+Benefits of a multi-agent system
+
+Research work involves open-ended problems where it’s very difficult to predict the required steps in advance. You can’t hardcode a fixed path for exploring complex topics, as the process is inherently dynamic and path-dependent. When people conduct research, they tend to continuously update their approach based on discoveries, following leads that emerge during investigation.
+
+This unpredictability makes AI agents particularly well-suited for research tasks. Research demands the flexibility to pivot or explore tangential connections as the investigation unfolds. The model must operate autonomously for many turns, making decisions about which directions to pursue based on intermediate findings. A linear, one-shot pipeline cannot handle these tasks.
+
+The essence of search is compression: distilling insights from a vast corpus. Subagents facilitate compression by operating in parallel with their own context windows, exploring different aspects of the question simultaneously before condensing the most important tokens for the lead research agent. Each subagent also provides separation of concerns—distinct tools, prompts, and exploration trajectories—which reduces path dependency and enables thorough, independent investigations.
+
+Once intelligence reaches a threshold, multi-agent systems become a vital way to scale performance. For instance, although individual humans have become more intelligent in the last 100,000 years, human societies have become exponentially more capable in the information age because of our collective intelligence and ability to coordinate. Even generally-intelligent agents face limits when operating as individuals; groups of agents can accomplish far more.
+
+Our internal evaluations show that multi-agent research systems excel especially for breadth-first queries that involve pursuing multiple independent directions simultaneously. We found that a multi-agent system with Claude Opus 4 as the lead agent and Claude Sonnet 4 subagents outperformed single-agent Claude Opus 4 by 90.2% on our internal research eval. For example, when asked to identify all the board members of the companies in the Information Technology S&P 500, the multi-agent system found the correct answers by decomposing this into tasks for subagents, while the single agent system failed to find the answer with slow, sequential searches.
+
+Multi-agent systems work mainly because they help spend enough tokens to solve the problem. In our analysis, three factors explained 95% of the performance variance in the BrowseComp evaluation (which tests the ability of browsing agents to locate hard-to-find information). We found that token usage by itself explains 80% of the variance, with the number of tool calls and the model choice as the two other explanatory factors. This finding validates our architecture that distributes work across agents with separate context windows to add more capacity for parallel reasoning. The latest Claude models act as large efficiency multipliers on token use, as upgrading to Claude Sonnet 4 is a larger performance gain than doubling the token budget on Claude Sonnet 3.7. Multi-agent architectures effectively scale token usage for tasks that exceed the limits of single agents.
+
+There is a downside: in practice, these architectures burn through tokens fast. In our data, agents typically use about 4× more tokens than chat interactions, and multi-agent systems use about 15× more tokens than chats. For economic viability, multi-agent systems require tasks where the value of the task is high enough to pay for the increased performance. Further, some domains that require all agents to share the same context or involve many dependencies between agents are not a good fit for multi-agent systems today. For instance, most coding tasks involve fewer truly parallelizable tasks than research, and LLM agents are not yet great at coordinating and delegating to other agents in real time. We’ve found that multi-agent systems excel at valuable tasks that involve heavy parallelization, information that exceeds single context windows, and interfacing with numerous complex tools.
+
+Architecture overview for Research
+
+Our Research system uses a multi-agent architecture with an orchestrator-worker pattern, where a lead agent coordinates the process while delegating to specialized subagents that operate in parallel.
+
+The multi-agent architecture in action: user queries flow through a lead agent that creates specialized subagents to search for different aspects in parallel.
+
+When a user submits a query, the lead agent analyzes it, develops a strategy, and spawns subagents to explore different aspects simultaneously. As shown in the diagram above, the subagents act as intelligent filters by iteratively using search tools to gather information, in this case on AI agent companies in 2025, and then returning a list of companies to the lead agent so it can compile a final answer.
+
+Traditional approaches using Retrieval Augmented Generation (RAG) use static retrieval. That is, they fetch some set of chunks that are most similar to an input query and use these chunks to generate a response. In contrast, our architecture uses a multi-step search that dynamically finds relevant information, adapts to new findings, and analyzes results to formulate high-quality answers.
+
+Process diagram showing the complete workflow of our multi-agent Research system. When a user submits a query, the system creates a LeadResearcher agent that enters an iterative research process. The LeadResearcher begins by thinking through the approach and saving its plan to Memory to persist the context, since if the context window exceeds 200,000 tokens it will be truncated and it is important to retain the plan. It then creates specialized Subagents (two are shown here, but it can be any number) with specific research tasks. Each Subagent independently performs web searches, evaluates tool results using interleaved thinking, and returns findings to the LeadResearcher. The LeadResearcher synthesizes these results and decides whether more research is needed—if so, it can create additional subagents or refine its strategy. Once sufficient information is gathered, the system exits the research loop and passes all findings to a CitationAgent, which processes the documents and research report to identify specific locations for citations. This ensures all claims are properly attributed to their sources. The final research results, complete with citations, are then returned to the user.
+
+Prompt engineering and evaluations for research agents
+
+Multi-agent systems have key differences from single-agent systems, including a rapid growth in coordination complexity. Early agents made errors like spawning 50 subagents for simple queries, scouring the web endlessly for nonexistent sources, and distracting each other with excessive updates. Since each agent is steered by a prompt, prompt engineering was our primary lever for improving these behaviors. Below are some principles we learned for prompting agents:
+
+Think like your agents. To iterate on prompts, you must understand their effects. To help us do this, we built simulations using our Console with the exact prompts and tools from our system, then watched agents work step-by-step. This immediately revealed failure modes: agents continuing when they already had sufficient results, using overly verbose search queries, or selecting incorrect tools. Effective prompting relies on developing an accurate mental model of the agent, which can make the most impactful changes obvious.
+
+Teach the orchestrator how to delegate. In our system, the lead agent decomposes queries into subtasks and describes them to subagents. Each subagent needs an objective, an output format, guidance on the tools and sources to use, and clear task boundaries. Without detailed task descriptions, agents duplicate work, leave gaps, or fail to find necessary information. We started by allowing the lead agent to give simple, short instructions like 'research the semiconductor shortage,' but found these instructions often were vague enough that subagents misinterpreted the task or performed the exact same searches as other agents. For instance, one subagent explored the 2021 automotive chip crisis while 2 others duplicated work investigating current 2025 supply chains, without an effective division of labor.
+
+Scale effort to query complexity. Agents struggle to judge appropriate effort for different tasks, so we embedded scaling rules in the prompts. Simple fact-finding requires just 1 agent with 3-10 tool calls, direct comparisons might need 2-4 subagents with 10-15 calls each, and complex research might use more than 10 subagents with clearly divided responsibilities. These explicit guidelines help the lead agent allocate resources efficiently and prevent overinvestment in simple queries, which was a common failure mode in our early versions.
+
+Tool design and selection are critical. Agent-tool interfaces are as critical as human-computer interfaces. Using the right tool is efficient—often, it’s strictly necessary. For instance, an agent searching the web for context that only exists in Slack is doomed from the start. With MCP servers that give the model access to external tools, this problem compounds, as agents encounter unseen tools with descriptions of wildly varying quality. We gave our agents explicit heuristics: for example, examine all available tools first, match tool usage to user intent, search the web for broad external exploration, or prefer specialized tools over generic ones. Bad tool descriptions can send agents down completely wrong paths, so each tool needs a distinct purpose and a clear description.
+
+Let agents improve themselves. We found that the Claude 4 models can be excellent prompt engineers. When given a prompt and a failure mode, they are able to diagnose why the agent is failing and suggest improvements. We even created a tool-testing agent—when given a flawed MCP tool, it attempts to use the tool and then rewrites the tool description to avoid failures. By testing the tool dozens of times, this agent found key nuances and bugs. This process for improving tool ergonomics resulted in a 40% decrease in task completion time for future agents using the new description, because they were able to avoid most mistakes.
+
+Start wide, then narrow down. Search strategy should mirror expert human research: explore the landscape before drilling into specifics. Agents often default to overly long, specific queries that return few results. We counteracted this tendency by prompting agents to start with short, broad queries, evaluate what’s available, then progressively narrow focus.
+
+Guide the thinking process. Extended thinking mode, which leads Claude to output additional tokens in a visible thinking process, can serve as a controllable scratchpad. The lead agent uses thinking to plan its approach, assessing which tools fit the task, determining query complexity and subagent count, and defining each subagent’s role. Our testing showed that extended thinking improved instruction-following, reasoning, and efficiency. Subagents also plan, then use interleaved thinking after tool results to evaluate quality, identify gaps, and refine their next query. This makes subagents more effective in adapting to any task.
+
+Parallel tool calling transforms speed and performance. Complex research tasks naturally involve exploring many sources. Our early agents executed sequential searches, which was painfully slow. For speed, we introduced two kinds of parallelization: (1) the lead agent spins up 3-5 subagents in parallel rather than serially; (2) the subagents use 3+ tools in parallel. These changes cut research time by up to 90% for complex queries, allowing Research to do more work in minutes instead of hours while covering more information than other systems.
+
+Our prompting strategy focuses on instilling good heuristics rather than rigid rules. We studied how skilled humans approach research tasks and encoded these strategies in our prompts—strategies like decomposing difficult questions into smaller tasks, carefully evaluating the quality of sources, adjusting search approaches based on new information, and recognizing when to focus on depth (investigating one topic in detail) vs. breadth (exploring many topics in parallel). We also proactively mitigated unintended side effects by setting explicit guardrails to prevent the agents from spiraling out of control. Finally, we focused on a fast iteration loop with observability and test cases.
+
+Effective evaluation of agents
+
+Good evaluations are essential for building reliable AI applications, and agents are no different. However, evaluating multi-agent systems presents unique challenges. Traditional evaluations often assume that the AI follows the same steps each time: given input X, the system should follow path Y to produce output Z. But multi-agent systems don't work this way. Even with identical starting points, agents might take completely different valid paths to reach their goal. One agent might search three sources while another searches ten, or they might use different tools to find the same answer. Because we don’t always know what the right steps are, we usually can't just check if agents followed the “correct” steps we prescribed in advance. Instead, we need flexible evaluation methods that judge whether agents achieved the right outcomes while also following a reasonable process.
+
+Start evaluating immediately with small samples. In early agent development, changes tend to have dramatic impacts because there is abundant low-hanging fruit. A prompt tweak might boost success rates from 30% to 80%. With effect sizes this large, you can spot changes with just a few test cases. We started with a set of about 20 queries representing real usage patterns. Testing these queries often allowed us to clearly see the impact of changes. We often hear that AI developer teams delay creating evals because they believe that only large evals with hundreds of test cases are useful. However, it’s best to start with small-scale testing right away with a few examples, rather than delaying until you can build more thorough evals.
+
+LLM-as-judge evaluation scales when done well. Research outputs are difficult to evaluate programmatically, since they are free-form text and rarely have a single correct answer. LLMs are a natural fit for grading outputs. We used an LLM judge that evaluated each output against criteria in a rubric: factual accuracy (do claims match sources?), citation accuracy (do the cited sources match the claims?), completeness (are all requested aspects covered?), source quality (did it use primary sources over lower-quality secondary sources?), and tool efficiency (did it use the right tools a reasonable number of times?). We experimented with multiple judges to evaluate each component, but found that a single LLM call with a single prompt outputting scores from 0.0-1.0 and a pass-fail grade was the most consistent and aligned with human judgements. This method was especially effective when the eval test cases did have a clear answer, and we could use the LLM judge to simply check if the answer was correct (i.e. did it accurately list the pharma companies with the top 3 largest R&D budgets?). Using an LLM as a judge allowed us to scalably evaluate hundreds of outputs.
+
+Human evaluation catches what automation misses. People testing agents find edge cases that evals miss. These include hallucinated answers on unusual queries, system failures, or subtle source selection biases. In our case, human testers noticed that our early agents consistently chose SEO-optimized content farms over authoritative but less highly-ranked sources like academic PDFs or personal blogs. Adding source quality heuristics to our prompts helped resolve this issue. Even in a world of automated evaluations, manual testing remains essential.
+
+Multi-agent systems have emergent behaviors, which arise without specific programming. For instance, small changes to the lead agent can unpredictably change how subagents behave. Success requires understanding interaction patterns, not just individual agent behavior. Therefore, the best prompts for these agents are not just strict instructions, but frameworks for collaboration that define the division of labor, problem-solving approaches, and effort budgets. Getting this right relies on careful prompting and tool design, solid heuristics, observability, and tight feedback loops. See the open-source prompts in our Cookbook for example prompts from our system.
+
+Production reliability and engineering challenges
+
+In traditional software, a bug might break a feature, degrade performance, or cause outages. In agentic systems, minor changes cascade into large behavioral changes, which makes it remarkably difficult to write code for complex agents that must maintain state in a long-running process.
+
+Agents are stateful and errors compound. Agents can run for long periods of time, maintaining state across many tool calls. This means we need to durably execute code and handle errors along the way. Without effective mitigations, minor system failures can be catastrophic for agents. When errors occur, we can't just restart from the beginning: restarts are expensive and frustrating for users. Instead, we built systems that can resume from where the agent was when the errors occurred. We also use the model’s intelligence to handle issues gracefully: for instance, letting the agent know when a tool is failing and letting it adapt works surprisingly well. We combine the adaptability of AI agents built on Claude with deterministic safeguards like retry logic and regular checkpoints.
+
+Debugging benefits from new approaches. Agents make dynamic decisions and are non-deterministic between runs, even with identical prompts. This makes debugging harder. For instance, users would report agents “not finding obvious information,” but we couldn't see why. Were the agents using bad search queries? Choosing poor sources? Hitting tool failures? Adding full production tracing let us diagnose why agents failed and fix issues systematically. Beyond standard observability, we monitor agent decision patterns and interaction structures—all without monitoring the contents of individual conversations, to maintain user privacy. This high-level observability helped us diagnose root causes, discover unexpected behaviors, and fix common failures.
+
+Deployment needs careful coordination. Agent systems are highly stateful webs of prompts, tools, and execution logic that run almost continuously. This means that whenever we deploy updates, agents might be anywhere in their process. We therefore need to prevent our well-meaning code changes from breaking existing agents. We can’t update every agent to the new version at the same time. Instead, we use rainbow deployments to avoid disrupting running agents, by gradually shifting traffic from old to new versions while keeping both running simultaneously.
+
+Synchronous execution creates bottlenecks. Currently, our lead agents execute subagents synchronously, waiting for each set of subagents to complete before proceeding. This simplifies coordination, but creates bottlenecks in the information flow between agents. For instance, the lead agent can’t steer subagents, subagents can’t coordinate, and the entire system can be blocked while waiting for a single subagent to finish searching. Asynchronous execution would enable additional parallelism: agents working concurrently and creating new subagents when needed. But this asynchronicity adds challenges in result coordination, state consistency, and error propagation across the subagents. As models can handle longer and more complex research tasks, we expect the performance gains will justify the complexity.
+
+Conclusion
+
+When building AI agents, the last mile often becomes most of the journey. Codebases that work on developer machines require significant engineering to become reliable production systems. The compound nature of errors in agentic systems means that minor issues for traditional software can derail agents entirely. One step failing can cause agents to explore entirely different trajectories, leading to unpredictable outcomes. For all the reasons described in this post, the gap between prototype and production is often wider than anticipated.
+
+Despite these challenges, multi-agent systems have proven valuable for open-ended research tasks. Users have said that Claude helped them find business opportunities they hadn’t considered, navigate complex healthcare options, resolve thorny technical bugs, and save up to days of work by uncovering research connections they wouldn't have found alone. Multi-agent research systems can operate reliably at scale with careful engineering, comprehensive testing, detail-oriented prompt and tool design, robust operational practices, and tight collaboration between research, product, and engineering teams who have a strong understanding of current agent capabilities. We're already seeing these systems transform how people solve complex problems.
+
+A Clio embedding plot showing the most common ways people are using the Research feature today. The top use case categories are developing software systems across specialized domains (10%), develop and optimize professional and technical content (8%), develop business growth and revenue generation strategies (8%), assist with academic research and educational material development (7%), and research and verify information about people, places, or organizations (5%).
+
+Acknowlegements
+
+Written by Jeremy Hadfield, Barry Zhang, Kenneth Lien, Florian Scholz, Jeremy Fox, and Daniel Ford. This work reflects the collective efforts of several teams across Anthropic who made the Research feature possible. Special thanks go to the Anthropic apps engineering team, whose dedication brought this complex multi-agent system to production. We're also grateful to our early users for their excellent feedback.
+
+Appendix
+
+Below are some additional miscellaneous tips for multi-agent systems.
+
+End-state evaluation of agents that mutate state over many turns. Evaluating agents that modify persistent state across multi-turn conversations presents unique challenges. Unlike read-only research tasks, each action can change the environment for subsequent steps, creating dependencies that traditional evaluation methods struggle to handle. We found success focusing on end-state evaluation rather than turn-by-turn analysis. Instead of judging whether the agent followed a specific process, evaluate whether it achieved the correct final state. This approach acknowledges that agents may find alternative paths to the same goal while still ensuring they deliver the intended outcome. For complex workflows, break evaluation into discrete checkpoints where specific state changes should have occurred, rather than attempting to validate every intermediate step.
+
+Long-horizon conversation management. Production agents often engage in conversations spanning hundreds of turns, requiring careful context management strategies. As conversations extend, standard context windows become insufficient, necessitating intelligent compression and memory mechanisms. We implemented patterns where agents summarize completed work phases and store essential information in external memory before proceeding to new tasks. When context limits approach, agents can spawn fresh subagents with clean contexts while maintaining continuity through careful handoffs. Further, they can retrieve stored context like the research plan from their memory rather than losing previous work when reaching the context limit. This distributed approach prevents context overflow while preserving conversation coherence across extended interactions.
+
+Subagent output to a filesystem to minimize the ‘game of telephone.’ Direct subagent outputs can bypass the main coordinator for certain types of results, improving both fidelity and performance. Rather than requiring subagents to communicate everything through the lead agent, implement artifact systems where specialized agents can create outputs that persist independently. Subagents call tools to store their work in external systems, then pass lightweight references back to the coordinator. This prevents information loss during multi-stage processing and reduces token overhead from copying large outputs through conversation history. The pattern works particularly well for structured outputs like code, reports, or data visualizations where the subagent's specialized prompt produces better results than filtering through a general coordinator.
+
+-------
+
+riting effective tools for agents — with agents
+
+Published Sep 11, 2025
+
+Agents are only as effective as the tools we give them. We share how to write high-quality tools and evaluations, and how you can boost performance by using Claude to optimize its tools for itself.
+
+The Model Context Protocol (MCP) can empower LLM agents with potentially hundreds of tools to solve real-world tasks. But how do we make those tools maximally effective?
+
+In this post, we describe our most effective techniques for improving performance in a variety of agentic AI systems1.
+
+We begin by covering how you can:
+
+Build and test prototypes of your tools
+
+Create and run comprehensive evaluations of your tools with agents
+
+Collaborate with agents like Claude Code to automatically increase the performance of your tools
+
+We conclude with key principles for writing high-quality tools we’ve identified along the way:
+
+Choosing the right tools to implement (and not to implement)
+
+Namespacing tools to define clear boundaries in functionality
+
+Returning meaningful context from tools back to agents
+
+Optimizing tool responses for token efficiency
+
+Prompt-engineering tool descriptions and specs
+
+This is an image depicting how an engineer might use Claude Code to evaluate the efficacy of agentic tools.
+
+Building an evaluation allows you to systematically measure the performance of your tools. You can use Claude Code to automatically optimize your tools against this evaluation.
+
+What is a tool?
+
+In computing, deterministic systems produce the same output every time given identical inputs, while non-deterministic systems—like agents—can generate varied responses even with the same starting conditions.
+
+When we traditionally write software, we’re establishing a contract between deterministic systems. For instance, a function call like getWeather(“NYC”) will always fetch the weather in New York City in the exact same manner every time it is called.
+
+Tools are a new kind of software which reflects a contract between deterministic systems and non-deterministic agents. When a user asks "Should I bring an umbrella today?,” an agent might call the weather tool, answer from general knowledge, or even ask a clarifying question about location first. Occasionally, an agent might hallucinate or even fail to grasp how to use a tool.
+
+This means fundamentally rethinking our approach when writing software for agents: instead of writing tools and MCP servers the way we’d write functions and APIs for other developers or systems, we need to design them for agents.
+
+Our goal is to increase the surface area over which agents can be effective in solving a wide range of tasks by using tools to pursue a variety of successful strategies. Fortunately, in our experience, the tools that are most “ergonomic” for agents also end up being surprisingly intuitive to grasp as humans.
+
+How to write tools
+
+In this section, we describe how you can collaborate with agents both to write and to improve the tools you give them. Start by standing up a quick prototype of your tools and testing them locally. Next, run a comprehensive evaluation to measure subsequent changes. Working alongside agents, you can repeat the process of evaluating and improving your tools until your agents achieve strong performance on real-world tasks.
+
+Building a prototype
+
+It can be difficult to anticipate which tools agents will find ergonomic and which tools they won’t without getting hands-on yourself. Start by standing up a quick prototype of your tools. If you’re using Claude Code to write your tools (potentially in one-shot), it helps to give Claude documentation for any software libraries, APIs, or SDKs (including potentially the MCP SDK) your tools will rely on. LLM-friendly documentation can commonly be found in flat llms.txt files on official documentation sites (here’s our API’s).
+
+Wrapping your tools in a local MCP server or Desktop extension (DXT) will allow you to connect and test your tools in Claude Code or the Claude Desktop app.
+
+To connect your local MCP server to Claude Code, run claude mcp add <name> <command> [args...].
+
+To connect your local MCP server or DXT to the Claude Desktop app, navigate to Settings > Developer or Settings > Extensions, respectively.
+
+Tools can also be passed directly into Anthropic API calls for programmatic testing.
+
+Test the tools yourself to identify any rough edges. Collect feedback from your users to build an intuition around the use-cases and prompts you expect your tools to enable.
+
+Running an evaluation
+
+Next, you need to measure how well Claude uses your tools by running an evaluation. Start by generating lots of evaluation tasks, grounded in real world uses. We recommend collaborating with an agent to help analyze your results and determine how to improve your tools. See this process end-to-end in our tool evaluation cookbook.
+
+This graph measures the test set accuracy of human-written vs. Claude-optimized Slack MCP servers.
+
+Held-out test set performance of our internal Slack tools
+
+Generating evaluation tasks
+
+With your early prototype, Claude Code can quickly explore your tools and create dozens of prompt and response pairs. Prompts should be inspired by real-world uses and be based on realistic data sources and services (for example, internal knowledge bases and microservices). We recommend you avoid overly simplistic or superficial “sandbox” environments that don’t stress-test your tools with sufficient complexity. Strong evaluation tasks might require multiple tool calls—potentially dozens.
+
+Here are some examples of strong tasks:
+
+Schedule a meeting with Jane next week to discuss our latest Acme Corp project. Attach the notes from our last project planning meeting and reserve a conference room.
+
+Customer ID 9182 reported that they were charged three times for a single purchase attempt. Find all relevant log entries and determine if any other customers were affected by the same issue.
+
+Customer Sarah Chen just submitted a cancellation request. Prepare a retention offer. Determine: (1) why they're leaving, (2) what retention offer would be most compelling, and (3) any risk factors we should be aware of before making an offer.
+
+And here are some weaker tasks:
+
+Schedule a meeting with jane@acme.corp next week.
+
+Search the payment logs for purchase_complete and customer_id=9182.
+
+Find the cancellation request by Customer ID 45892.
+
+Each evaluation prompt should be paired with a verifiable response or outcome. Your verifier can be as simple as an exact string comparison between ground truth and sampled responses, or as advanced as enlisting Claude to judge the response. Avoid overly strict verifiers that reject correct responses due to spurious differences like formatting, punctuation, or valid alternative phrasings.
+
+For each prompt-response pair, you can optionally also specify the tools you expect an agent to call in solving the task, to measure whether or not agents are successful in grasping each tool’s purpose during evaluation. However, because there might be multiple valid paths to solving tasks correctly, try to avoid overspecifying or overfitting to strategies.
+
+Running the evaluation
+
+We recommend running your evaluation programmatically with direct LLM API calls. Use simple agentic loops (while-loops wrapping alternating LLM API and tool calls): one loop for each evaluation task. Each evaluation agent should be given a single task prompt and your tools.
+
+In your evaluation agents’ system prompts, we recommend instructing agents to output not just structured response blocks (for verification), but also reasoning and feedback blocks. Instructing agents to output these before tool call and response blocks may increase LLMs’ effective intelligence by triggering chain-of-thought (CoT) behaviors.
+
+If you’re running your evaluation with Claude, you can turn on interleaved thinking for similar functionality “off-the-shelf”. This will help you probe why agents do or don’t call certain tools and highlight specific areas of improvement in tool descriptions and specs.
+
+As well as top-level accuracy, we recommend collecting other metrics like the total runtime of individual tool calls and tasks, the total number of tool calls, the total token consumption, and tool errors. Tracking tool calls can help reveal common workflows that agents pursue and offer some opportunities for tools to consolidate.
+
+This graph measures the test set accuracy of human-written vs. Claude-optimized Asana MCP servers.
+
+Held-out test set performance of our internal Asana tools
+
+Analyzing results
+
+Agents are your helpful partners in spotting issues and providing feedback on everything from contradictory tool descriptions to inefficient tool implementations and confusing tool schemas. However, keep in mind that what agents omit in their feedback and responses can often be more important than what they include. LLMs don’t always say what they mean.
+
+Observe where your agents get stumped or confused. Read through your evaluation agents’ reasoning and feedback (or CoT) to identify rough edges. Review the raw transcripts (including tool calls and tool responses) to catch any behavior not explicitly described in the agent’s CoT. Read between the lines; remember that your evaluation agents don’t necessarily know the correct answers and strategies.
+
+Analyze your tool calling metrics. Lots of redundant tool calls might suggest some rightsizing of pagination or token limit parameters is warranted; lots of tool errors for invalid parameters might suggest tools could use clearer descriptions or better examples. When we launched Claude’s web search tool, we identified that Claude was needlessly appending 2025 to the tool’s query parameter, biasing search results and degrading performance (we steered Claude in the right direction by improving the tool description).
+
+Collaborating with agents
+
+You can even let agents analyze your results and improve your tools for you. Simply concatenate the transcripts from your evaluation agents and paste them into Claude Code. Claude is an expert at analyzing transcripts and refactoring lots of tools all at once—for example, to ensure tool implementations and descriptions remain self-consistent when new changes are made.
+
+In fact, most of the advice in this post came from repeatedly optimizing our internal tool implementations with Claude Code. Our evaluations were created on top of our internal workspace, mirroring the complexity of our internal workflows, including real projects, documents, and messages.
+
+We relied on held-out test sets to ensure we did not overfit to our “training” evaluations. These test sets revealed that we could extract additional performance improvements even beyond what we achieved with "expert" tool implementations—whether those tools were manually written by our researchers or generated by Claude itself.
+
+In the next section, we’ll share some of what we learned from this process.
+
+Principles for writing effective tools
+
+In this section, we distill our learnings into a few guiding principles for writing effective tools.
+
+Choosing the right tools for agents
+
+More tools don’t always lead to better outcomes. A common error we’ve observed is tools that merely wrap existing software functionality or API endpoints—whether or not the tools are appropriate for agents. This is because agents have distinct “affordances” to traditional software—that is, they have different ways of perceiving the potential actions they can take with those tools
+
+LLM agents have limited "context" (that is, there are limits to how much information they can process at once), whereas computer memory is cheap and abundant. Consider the task of searching for a contact in an address book. Traditional software programs can efficiently store and process a list of contacts one at a time, checking each one before moving on.
+
+However, if an LLM agent uses a tool that returns ALL contacts and then has to read through each one token-by-token, it's wasting its limited context space on irrelevant information (imagine searching for a contact in your address book by reading each page from top-to-bottom—that is, via brute-force search). The better and more natural approach (for agents and humans alike) is to skip to the relevant page first (perhaps finding it alphabetically).
+
+We recommend building a few thoughtful tools targeting specific high-impact workflows, which match your evaluation tasks and scaling up from there. In the address book case, you might choose to implement a search_contacts or message_contact tool instead of a list_contacts tool.
+
+Tools can consolidate functionality, handling potentially multiple discrete operations (or API calls) under the hood. For example, tools can enrich tool responses with related metadata or handle frequently chained, multi-step tasks in a single tool call.
+
+Here are some examples:
+
+Instead of implementing a list_users, list_events, and create_event tools, consider implementing a schedule_event tool which finds availability and schedules an event.
+
+Instead of implementing a read_logs tool, consider implementing a search_logs tool which only returns relevant log lines and some surrounding context.
+
+Instead of implementing get_customer_by_id, list_transactions, and list_notes tools, implement a get_customer_context tool which compiles all of a customer’s recent & relevant information all at once.
+
+Make sure each tool you build has a clear, distinct purpose. Tools should enable agents to subdivide and solve tasks in much the same way that a human would, given access to the same underlying resources, and simultaneously reduce the context that would have otherwise been consumed by intermediate outputs.
+
+Too many tools or overlapping tools can also distract agents from pursuing efficient strategies. Careful, selective planning of the tools you build (or don’t build) can really pay off.
+
+Namespacing your tools
+
+Your AI agents will potentially gain access to dozens of MCP servers and hundreds of different tools–including those by other developers. When tools overlap in function or have a vague purpose, agents can get confused about which ones to use.
+
+Namespacing (grouping related tools under common prefixes) can help delineate boundaries between lots of tools; MCP clients sometimes do this by default. For example, namespacing tools by service (e.g., asana_search, jira_search) and by resource (e.g., asana_projects_search, asana_users_search), can help agents select the right tools at the right time.
+
+We have found selecting between prefix- and suffix-based namespacing to have non-trivial effects on our tool-use evaluations. Effects vary by LLM and we encourage you to choose a naming scheme according to your own evaluations.
+
+Agents might call the wrong tools, call the right tools with the wrong parameters, call too few tools, or process tool responses incorrectly. By selectively implementing tools whose names reflect natural subdivisions of tasks, you simultaneously reduce the number of tools and tool descriptions loaded into the agent’s context and offload agentic computation from the agent’s context back into the tool calls themselves. This reduces an agent’s overall risk of making mistakes.
+
+Returning meaningful context from your tools
+
+In the same vein, tool implementations should take care to return only high signal information back to agents. They should prioritize contextual relevance over flexibility, and eschew low-level technical identifiers (for example: uuid, 256px_image_url, mime_type). Fields like name, image_url, and file_type are much more likely to directly inform agents’ downstream actions and responses.
+
+Agents also tend to grapple with natural language names, terms, or identifiers significantly more successfully than they do with cryptic identifiers. We’ve found that merely resolving arbitrary alphanumeric UUIDs to more semantically meaningful and interpretable language (or even a 0-indexed ID scheme) significantly improves Claude’s precision in retrieval tasks by reducing hallucinations.
+
+In some instances, agents may require the flexibility to interact with both natural language and technical identifiers outputs, if only to trigger downstream tool calls (for example, search_user(name=’jane’) → send_message(id=12345)). You can enable both by exposing a simple response_format enum parameter in your tool, allowing your agent to control whether tools return “concise” or “detailed” responses (images below).
+
+You can add more formats for even greater flexibility, similar to GraphQL where you can choose exactly which pieces of information you want to receive. Here is an example ResponseFormat enum to control tool response verbosity:
+
+enum ResponseFormat {
+
+   DETAILED = "detailed",
+
+   CONCISE = "concise"
+
+}
+
+Copy
+
+Here’s an example of a detailed tool response (206 tokens):
+
+This code snippet depicts an example of a detailed tool response.
+
+Here’s an example of a concise tool response (72 tokens):
+
+This code snippet depicts a concise tool response.
+
+Slack threads and thread replies are identified by unique thread_ts which are required to fetch thread replies. thread_ts and other IDs (channel_id, user_id) can be retrieved from a “detailed” tool response to enable further tool calls that require these. “concise” tool responses return only thread content and exclude IDs. In this example, we use ~⅓ of the tokens with “concise” tool responses.
+
+Even your tool response structure—for example XML, JSON, or Markdown—can have an impact on evaluation performance: there is no one-size-fits-all solution. This is because LLMs are trained on next-token prediction and tend to perform better with formats that match their training data. The optimal response structure will vary widely by task and agent. We encourage you to select the best response structure based on your own evaluation.
+
+Optimizing tool responses for token efficiency
+
+Optimizing the quality of context is important. But so is optimizing the quantity of context returned back to agents in tool responses.
+
+We suggest implementing some combination of pagination, range selection, filtering, and/or truncation with sensible default parameter values for any tool responses that could use up lots of context. For Claude Code, we restrict tool responses to 25,000 tokens by default. We expect the effective context length of agents to grow over time, but the need for context-efficient tools to remain.
+
+If you choose to truncate responses, be sure to steer agents with helpful instructions. You can directly encourage agents to pursue more token-efficient strategies, like making many small and targeted searches instead of a single, broad search for a knowledge retrieval task. Similarly, if a tool call raises an error (for example, during input validation), you can prompt-engineer your error responses to clearly communicate specific and actionable improvements, rather than opaque error codes or tracebacks.
+
+Here’s an example of a truncated tool response:
+
+This image depicts an example of a truncated tool response.
+
+Here’s an example of an unhelpful error response:
+
+This image depicts an example of an unhelpful tool response. 
+
+Here’s an example of a helpful error response:
+
+This image depicts an example of a helpful error response.
+
+Tool truncation and error responses can steer agents towards more token-efficient tool-use behaviors (using filters or pagination) or give examples of correctly formatted tool inputs.
+
+Prompt-engineering your tool descriptions
+
+We now come to one of the most effective methods for improving tools: prompt-engineering your tool descriptions and specs. Because these are loaded into your agents’ context, they can collectively steer agents toward effective tool-calling behaviors.
+
+When writing tool descriptions and specs, think of how you would describe your tool to a new hire on your team. Consider the context that you might implicitly bring—specialized query formats, definitions of niche terminology, relationships between underlying resources—and make it explicit. Avoid ambiguity by clearly describing (and enforcing with strict data models) expected inputs and outputs. In particular, input parameters should be unambiguously named: instead of a parameter named user, try a parameter named user_id.
+
+With your evaluation you can measure the impact of your prompt engineering with greater confidence. Even small refinements to tool descriptions can yield dramatic improvements. Claude Sonnet 3.5 achieved state-of-the-art performance on the SWE-bench Verified evaluation after we made precise refinements to tool descriptions, dramatically reducing error rates and improving task completion.
+
+You can find other best practices for tool definitions in our Developer Guide. If you’re building tools for Claude, we also recommend reading about how tools are dynamically loaded into Claude’s system prompt. Lastly, if you’re writing tools for an MCP server, tool annotations help disclose which tools require open-world access or make destructive changes.
+
+Looking ahead
+
+To build effective tools for agents, we need to re-orient our software development practices from predictable, deterministic patterns to non-deterministic ones.
+
+Through the iterative, evaluation-driven process we’ve described in this post, we've identified consistent patterns in what makes tools successful: Effective tools are intentionally and clearly defined, use agent context judiciously, can be combined together in diverse workflows, and enable agents to intuitively solve real-world tasks.
+
+In the future, we expect the specific mechanisms through which agents interact with the world to evolve—from updates to the MCP protocol to upgrades to the underlying LLMs themselves. With a systematic, evaluation-driven approach to improving tools for agents, we can ensure that as agents become more capable, the tools they use will evolve alongside them.
+
+Acknowledgements
+
+Written by Ken Aizawa with valuable contributions from colleagues across Research (Barry Zhang, Zachary Witten, Daniel Jiang, Sami Al-Sheikh, Matt Bell, Maggie Vo), MCP (Theodora Chu, John Welsh, David Soria Parra, Adam Jones), Product Engineering (Santiago Seira), Marketing (Molly Vorwerck), Design (Drew Roper), and Applied AI (Christian Ryan, Alexander Bricken).
+
+1Beyond training the underlying LLMs themselves.
+
+-------
+
+Effective context engineering for AI agents
+
+Published Sep 29, 2025
+
+Context is a critical but finite resource for AI agents. In this post, we explore strategies for effectively curating and managing the context that powers them.
+
+After a few years of prompt engineering being the focus of attention in applied AI, a new term has come to prominence: context engineering. Building with language models is becoming less about finding the right words and phrases for your prompts, and more about answering the broader question of “what configuration of context is most likely to generate our model’s desired behavior?"
+
+Context refers to the set of tokens included when sampling from a large-language model (LLM). The engineering problem at hand is optimizing the utility of those tokens against the inherent constraints of LLMs in order to consistently achieve a desired outcome. Effectively wrangling LLMs often requires thinking in context — in other words: considering the holistic state available to the LLM at any given time and what potential behaviors that state might yield.
+
+In this post, we’ll explore the emerging art of context engineering and offer a refined mental model for building steerable, effective agents.
+
+Context engineering vs. prompt engineering
+
+At Anthropic, we view context engineering as the natural progression of prompt engineering. Prompt engineering refers to methods for writing and organizing LLM instructions for optimal outcomes (see our docs for an overview and useful prompt engineering strategies). Context engineering refers to the set of strategies for curating and maintaining the optimal set of tokens (information) during LLM inference, including all the other information that may land there outside of the prompts.
+
+In the early days of engineering with LLMs, prompting was the biggest component of AI engineering work, as the majority of use cases outside of everyday chat interactions required prompts optimized for one-shot classification or text generation tasks. As the term implies, the primary focus of prompt engineering is how to write effective prompts, particularly system prompts. However, as we move towards engineering more capable agents that operate over multiple turns of inference and longer time horizons, we need strategies for managing the entire context state (system instructions, tools, Model Context Protocol (MCP), external data, message history, etc).
+
+An agent running in a loop generates more and more data that could be relevant for the next turn of inference, and this information must be cyclically refined. Context engineering is the art and science of curating what will go into the limited context window from that constantly evolving universe of possible information.
+
+Prompt engineering vs. context engineering
+
+In contrast to the discrete task of writing a prompt, context engineering is iterative and the curation phase happens each time we decide what to pass to the model.
+
+Why context engineering is important to building capable agents
+
+Despite their speed and ability to manage larger and larger volumes of data, we’ve observed that LLMs, like humans, lose focus or experience confusion at a certain point. Studies on needle-in-a-haystack style benchmarking have uncovered the concept of context rot: as the number of tokens in the context window increases, the model’s ability to accurately recall information from that context decreases.
+
+While some models exhibit more gentle degradation than others, this characteristic emerges across all models. Context, therefore, must be treated as a finite resource with diminishing marginal returns. Like humans, who have limited working memory capacity, LLMs have an “attention budget” that they draw on when parsing large volumes of context. Every new token introduced depletes this budget by some amount, increasing the need to carefully curate the tokens available to the LLM.
+
+This attention scarcity stems from architectural constraints of LLMs. LLMs are based on the transformer architecture, which enables every token to attend to every other token across the entire context. This results in n² pairwise relationships for n tokens.
+
+As its context length increases, a model's ability to capture these pairwise relationships gets stretched thin, creating a natural tension between context size and attention focus. Additionally, models develop their attention patterns from training data distributions where shorter sequences are typically more common than longer ones. This means models have less experience with, and fewer specialized parameters for, context-wide dependencies.
+
+Techniques like position encoding interpolation allow models to handle longer sequences by adapting them to the originally trained smaller context, though with some degradation in token position understanding. These factors create a performance gradient rather than a hard cliff: models remain highly capable at longer contexts but may show reduced precision for information retrieval and long-range reasoning compared to their performance on shorter contexts.
+
+These realities mean that thoughtful context engineering is essential for building capable agents.
+
+The anatomy of effective context
+
+Given that LLMs are constrained by a finite attention budget, good context engineering means finding the smallest possible set of high-signal tokens that maximize the likelihood of some desired outcome. Implementing this practice is much easier said than done, but in the following section, we outline what this guiding principle means in practice across the different components of context.
+
+System prompts should be extremely clear and use simple, direct language that presents ideas at the right altitude for the agent. The right altitude is the Goldilocks zone between two common failure modes. At one extreme, we see engineers hardcoding complex, brittle logic in their prompts to elicit exact agentic behavior. This approach creates fragility and increases maintenance complexity over time. At the other extreme, engineers sometimes provide vague, high-level guidance that fails to give the LLM concrete signals for desired outputs or falsely assumes shared context. The optimal altitude strikes a balance: specific enough to guide behavior effectively, yet flexible enough to provide the model with strong heuristics to guide behavior.
+
+Calibrating the system prompt in the process of context engineering.
+
+At one end of the spectrum, we see brittle if-else hardcoded prompts, and at the other end we see prompts that are overly general or falsely assume shared context.
+
+We recommend organizing prompts into distinct sections (like <background_information>, <instructions>, ## Tool guidance, ## Output description, etc) and using techniques like XML tagging or Markdown headers to delineate these sections, although the exact formatting of prompts is likely becoming less important as models become more capable.
+
+Regardless of how you decide to structure your system prompt, you should be striving for the minimal set of information that fully outlines your expected behavior. (Note that minimal does not necessarily mean short; you still need to give the agent sufficient information up front to ensure it adheres to the desired behavior.) It’s best to start by testing a minimal prompt with the best model available to see how it performs on your task, and then add clear instructions and examples to improve performance based on failure modes found during initial testing.
+
+Tools allow agents to operate with their environment and pull in new, additional context as they work. Because tools define the contract between agents and their information/action space, it’s extremely important that tools promote efficiency, both by returning information that is token efficient and by encouraging efficient agent behaviors.
+
+In Writing tools for AI agents – with AI agents, we discussed building tools that are well understood by LLMs and have minimal overlap in functionality. Similar to the functions of a well-designed codebase, tools should be self-contained, robust to error, and extremely clear with respect to their intended use. Input parameters should similarly be descriptive, unambiguous, and play to the inherent strengths of the model.
+
+One of the most common failure modes we see is bloated tool sets that cover too much functionality or lead to ambiguous decision points about which tool to use. If a human engineer can’t definitively say which tool should be used in a given situation, an AI agent can’t be expected to do better. As we’ll discuss later, curating a minimal viable set of tools for the agent can also lead to more reliable maintenance and pruning of context over long interactions.
+
+Providing examples, otherwise known as few-shot prompting, is a well known best practice that we continue to strongly advise. However, teams will often stuff a laundry list of edge cases into a prompt in an attempt to articulate every possible rule the LLM should follow for a particular task. We do not recommend this. Instead, we recommend working to curate a set of diverse, canonical examples that effectively portray the expected behavior of the agent. For an LLM, examples are the “pictures” worth a thousand words.
+
+Our overall guidance across the different components of context (system prompts, tools, examples, message history, etc) is to be thoughtful and keep your context informative, yet tight. Now let's dive into dynamically retrieving context at runtime.
+
+Context retrieval and agentic search
+
+In Building effective AI agents, we highlighted the differences between LLM-based workflows and agents. Since we wrote that post, we’ve gravitated towards a simple definition for agents: LLMs autonomously using tools in a loop.
+
+Working alongside our customers, we’ve seen the field converging on this simple paradigm. As the underlying models become more capable, the level of autonomy of agents can scale: smarter models allow agents to independently navigate nuanced problem spaces and recover from errors.
+
+We’re now seeing a shift in how engineers think about designing context for agents. Today, many AI-native applications employ some form of embedding-based pre-inference time retrieval to surface important context for the agent to reason over. As the field transitions to more agentic approaches, we increasingly see teams augmenting these retrieval systems with “just in time” context strategies.
+
+Rather than pre-processing all relevant data up front, agents built with the “just in time” approach maintain lightweight identifiers (file paths, stored queries, web links, etc.) and use these references to dynamically load data into context at runtime using tools. Anthropic’s agentic coding solution Claude Code uses this approach to perform complex data analysis over large databases. The model can write targeted queries, store results, and leverage Bash commands like head and tail to analyze large volumes of data without ever loading the full data objects into context. This approach mirrors human cognition: we generally don’t memorize entire corpuses of information, but rather introduce external organization and indexing systems like file systems, inboxes, and bookmarks to retrieve relevant information on demand.
+
+Beyond storage efficiency, the metadata of these references provides a mechanism to efficiently refine behavior, whether explicitly provided or intuitive. To an agent operating in a file system, the presence of a file named test_utils.py in a tests folder implies a different purpose than a file with the same name located in src/core_logic/ Folder hierarchies, naming conventions, and timestamps all provide important signals that help both humans and agents understand how and when to utilize information.
+
+Letting agents navigate and retrieve data autonomously also enables progressive disclosure—in other words, allows agents to incrementally discover relevant context through exploration. Each interaction yields context that informs the next decision: file sizes suggest complexity; naming conventions hint at purpose; timestamps can be a proxy for relevance. Agents can assemble understanding layer by layer, maintaining only what's necessary in working memory and leveraging note-taking strategies for additional persistence. This self-managed context window keeps the agent focused on relevant subsets rather than drowning in exhaustive but potentially irrelevant information.
+
+Of course, there's a trade-off: runtime exploration is slower than retrieving pre-computed data. Not only that, but opinionated and thoughtful engineering is required to ensure that an LLM has the right tools and heuristics for effectively navigating its information landscape. Without proper guidance, an agent can waste context by misusing tools, chasing dead-ends, or failing to identify key information.
+
+In certain settings, the most effective agents might employ a hybrid strategy, retrieving some data up front for speed, and pursuing further autonomous exploration at its discretion. The decision boundary for the ‘right’ level of autonomy depends on the task. Claude Code is an agent that employs this hybrid model: CLAUDE.md files are naively dropped into context up front, while primitives like glob and grep allow it to navigate its environment and retrieve files just-in-time, effectively bypassing the issues of stale indexing and complex syntax trees.
+
+The hybrid strategy might be better suited for contexts with less dynamic content, such as legal or finance work. As model capabilities improve, agentic design will trend towards letting intelligent models act intelligently, with progressively less human curation. Given the rapid pace of progress in the field, "do the simplest thing that works" will likely remain our best advice for teams building agents on top of Claude.
+
+Context engineering for long-horizon tasks
+
+Long-horizon tasks require agents to maintain coherence, context, and goal-directed behavior over sequences of actions where the token count exceeds the LLM’s context window. For tasks that span tens of minutes to multiple hours of continuous work, like large codebase migrations or comprehensive research projects, agents require specialized techniques to work around the context window size limitation.
+
+Waiting for larger context windows might seem like an obvious tactic. But it's likely that for the foreseeable future, context windows of all sizes will be subject to context pollution and information relevance concerns—at least for situations where the strongest agent performance is desired. To enable agents to work effectively across extended time horizons, we've developed a few techniques that address these context pollution constraints directly: compaction, structured note-taking, and multi-agent architectures.
+
+Compaction
+
+Compaction is the practice of taking a conversation nearing the context window limit, summarizing its contents, and reinitiating a new context window with the summary. Compaction typically serves as the first lever in context engineering to drive better long-term coherence. At its core, compaction distills the contents of a context window in a high-fidelity manner, enabling the agent to continue with minimal performance degradation.
+
+In Claude Code, for example, we implement this by passing the message history to the model to summarize and compress the most critical details. The model preserves architectural decisions, unresolved bugs, and implementation details while discarding redundant tool outputs or messages. The agent can then continue with this compressed context plus the five most recently accessed files. Users get continuity without worrying about context window limitations.
+
+The art of compaction lies in the selection of what to keep versus what to discard, as overly aggressive compaction can result in the loss of subtle but critical context whose importance only becomes apparent later. For engineers implementing compaction systems, we recommend carefully tuning your prompt on complex agent traces. Start by maximizing recall to ensure your compaction prompt captures every relevant piece of information from the trace, then iterate to improve precision by eliminating superfluous content.
+
+An example of low-hanging superfluous content is clearing tool calls and results – once a tool has been called deep in the message history, why would the agent need to see the raw result again? One of the safest lightest touch forms of compaction is tool result clearing, most recently launched as a feature on the Claude Developer Platform.
+
+Structured note-taking
+
+Structured note-taking, or agentic memory, is a technique where the agent regularly writes notes persisted to memory outside of the context window. These notes get pulled back into the context window at later times.
+
+This strategy provides persistent memory with minimal overhead. Like Claude Code creating a to-do list, or your custom agent maintaining a NOTES.md file, this simple pattern allows the agent to track progress across complex tasks, maintaining critical context and dependencies that would otherwise be lost across dozens of tool calls.
+
+Claude playing Pokémon demonstrates how memory transforms agent capabilities in non-coding domains. The agent maintains precise tallies across thousands of game steps—tracking objectives like "for the last 1,234 steps I've been training my Pokémon in Route 1, Pikachu has gained 8 levels toward the target of 10." Without any prompting about memory structure, it develops maps of explored regions, remembers which key achievements it has unlocked, and maintains strategic notes of combat strategies that help it learn which attacks work best against different opponents.
+
+After context resets, the agent reads its own notes and continues multi-hour training sequences or dungeon explorations. This coherence across summarization steps enables long-horizon strategies that would be impossible when keeping all the information in the LLM’s context window alone.
+
+As part of our Sonnet 4.5 launch, we released a memory tool in public beta on the Claude Developer Platform that makes it easier to store and consult information outside the context window through a file-based system. This allows agents to build up knowledge bases over time, maintain project state across sessions, and reference previous work without keeping everything in context.
+
+Sub-agent architectures
+
+Sub-agent architectures provide another way around context limitations. Rather than one agent attempting to maintain state across an entire project, specialized sub-agents can handle focused tasks with clean context windows. The main agent coordinates with a high-level plan while subagents perform deep technical work or use tools to find relevant information. Each subagent might explore extensively, using tens of thousands of tokens or more, but returns only a condensed, distilled summary of its work (often 1,000-2,000 tokens).
+
+This approach achieves a clear separation of concerns—the detailed search context remains isolated within sub-agents, while the lead agent focuses on synthesizing and analyzing the results. This pattern, discussed in How we built our multi-agent research system, showed a substantial improvement over single-agent systems on complex research tasks.
+
+The choice between these approaches depends on task characteristics. For example:
+
+Compaction maintains conversational flow for tasks requiring extensive back-and-forth;
+
+Note-taking excels for iterative development with clear milestones;
+
+Multi-agent architectures handle complex research and analysis where parallel exploration pays dividends.
+
+Even as models continue to improve, the challenge of maintaining coherence across extended interactions will remain central to building more effective agents.
+
+Conclusion
+
+Context engineering represents a fundamental shift in how we build with LLMs. As models become more capable, the challenge isn't just crafting the perfect prompt—it's thoughtfully curating what information enters the model's limited attention budget at each step. Whether you're implementing compaction for long-horizon tasks, designing token-efficient tools, or enabling agents to explore their environment just-in-time, the guiding principle remains the same: find the smallest set of high-signal tokens that maximize the likelihood of your desired outcome.
+
+The techniques we've outlined will continue evolving as models improve. We're already seeing that smarter models require less prescriptive engineering, allowing agents to operate with more autonomy. But even as capabilities scale, treating context as a precious, finite resource will remain central to building reliable, effective agents.
+
+Get started with context engineering in the Claude Developer Platform today, and access helpful tips and best practices via our memory and context management cookbook.
+
+---------
+
+ffective harnesses for long-running agents
+
+Published Nov 26, 2025
+
+Agents still face challenges working across many context windows. We looked to human engineers for inspiration in creating a more effective harness for long-running agents.
+
+As AI agents become more capable, developers are increasingly asking them to take on complex tasks requiring work that spans hours, or even days. However, getting agents to make consistent progress across multiple context windows remains an open problem.
+
+The core challenge of long-running agents is that they must work in discrete sessions, and each new session begins with no memory of what came before. Imagine a software project staffed by engineers working in shifts, where each new engineer arrives with no memory of what happened on the previous shift. Because context windows are limited, and because most complex projects cannot be completed within a single window, agents need a way to bridge the gap between coding sessions.
+
+We developed a two-fold solution to enable the Claude Agent SDK to work effectively across many context windows: an initializer agent that sets up the environment on the first run, and a coding agent that is tasked with making incremental progress in every session, while leaving clear artifacts for the next session. You can find code examples in the accompanying quickstart.
+
+The long-running agent problem
+
+The Claude Agent SDK is a powerful, general-purpose agent harness adept at coding, as well as other tasks that require the model to use tools to gather context, plan, and execute. It has context management capabilities such as compaction, which enables an agent to work on a task without exhausting the context window. Theoretically, given this setup, it should be possible for an agent to continue to do useful work for an arbitrarily long time.
+
+However, compaction isn’t sufficient. Out of the box, even a frontier coding model like Opus 4.5 running on the Claude Agent SDK in a loop across multiple context windows will fall short of building a production-quality web app if it’s only given a high-level prompt, such as “build a clone of claude.ai.”
+
+Claude’s failures manifested in two patterns. First, the agent tended to try to do too much at once—essentially to attempt to one-shot the app. Often, this led to the model running out of context in the middle of its implementation, leaving the next session to start with a feature half-implemented and undocumented. The agent would then have to guess at what had happened, and spend substantial time trying to get the basic app working again. This happens even with compaction, which doesn’t always pass perfectly clear instructions to the next agent.
+
+A second failure mode would often occur later in a project. After some features had already been built, a later agent instance would look around, see that progress had been made, and declare the job done.
+
+This decomposes the problem into two parts. First, we need to set up an initial environment that lays the foundation for all the features that a given prompt requires, which sets up the agent to work step-by-step and feature-by-feature. Second, we should prompt each agent to make incremental progress towards its goal while also leaving the environment in a clean state at the end of a session. By “clean state” we mean the kind of code that would be appropriate for merging to a main branch: there are no major bugs, the code is orderly and well-documented, and in general, a developer could easily begin work on a new feature without first having to clean up an unrelated mess.
+
+When experimenting internally, we addressed these problems using a two-part solution:
+
+Initializer agent: The very first agent session uses a specialized prompt that asks the model to set up the initial environment: an init.sh script, a claude-progress.txt file that keeps a log of what agents have done, and an initial git commit that shows what files were added.
+
+Coding agent: Every subsequent session asks the model to make incremental progress, then leave structured updates.1
+
+The key insight here was finding a way for agents to quickly understand the state of work when starting with a fresh context window, which is accomplished with the claude-progress.txt file alongside the git history. Inspiration for these practices came from knowing what effective software engineers do every day.
+
+Environment management
+
+In the updated Claude 4 prompting guide, we shared some best practices for multi-context window workflows, including a harness structure that uses “a different prompt for the very first context window.” This “different prompt” requests that the initializer agent set up the environment with all the necessary context that future coding agents will need to work effectively. Here, we provide a deeper dive on some of the key components of such an environment.
+
+Feature list
+
+To address the problem of the agent one-shotting an app or prematurely considering the project complete, we prompted the initializer agent to write a comprehensive file of feature requirements expanding on the user’s initial prompt. In the claude.ai clone example, this meant over 200 features, such as “a user can open a new chat, type in a query, press enter, and see an AI response.” These features were all initially marked as “failing” so that later coding agents would have a clear outline of what full functionality looked like.
+
+{
+
+    "category": "functional",
+
+    "description": "New chat button creates a fresh conversation",
+
+    "steps": [
+
+      "Navigate to main interface",
+
+      "Click the 'New Chat' button",
+
+      "Verify a new conversation is created",
+
+      "Check that chat area shows welcome state",
+
+      "Verify conversation appears in sidebar"
+
+    ],
+
+    "passes": false
+
+  }
+
+Copy
+
+We prompt coding agents to edit this file only by changing the status of a passes field, and we use strongly-worded instructions like “It is unacceptable to remove or edit tests because this could lead to missing or buggy functionality.” After some experimentation, we landed on using JSON for this, as the model is less likely to inappropriately change or overwrite JSON files compared to Markdown files.
+
+Incremental progress
+
+Given this initial environment scaffolding, the next iteration of the coding agent was then asked to work on only one feature at a time. This incremental approach turned out to be critical to addressing the agent’s tendency to do too much at once.
+
+Once working incrementally, it’s still essential that the model leaves the environment in a clean state after making a code change. In our experiments, we found that the best way to elicit this behavior was to ask the model to commit its progress to git with descriptive commit messages and to write summaries of its progress in a progress file. This allowed the model to use git to revert bad code changes and recover working states of the code base.
+
+These approaches also increased efficiency, as they eliminated the need for an agent to have to guess at what had happened and spend its time trying to get the basic app working again.
+
+Testing
+
+One final major failure mode that we observed was Claude’s tendency to mark a feature as complete without proper testing. Absent explicit prompting, Claude tended to make code changes, and even do testing with unit tests or curl commands against a development server, but would fail recognize that the feature didn’t work end-to-end.
+
+In the case of building a web app, Claude mostly did well at verifying features end-to-end once explicitly prompted to use browser automation tools and do all testing as a human user would.
+
+ Screenshots taken by Claude through the Puppeteer MCP server as it tested the claude.ai clone. 
+
+Screenshots taken by Claude through the Puppeteer MCP server as it tested the claude.ai clone.
+
+Providing Claude with these kinds of testing tools dramatically improved performance, as the agent was able to identify and fix bugs that weren’t obvious from the code alone.
+
+Some issues remain, like limitations to Claude’s vision and to browser automation tools making it difficult to identify every kind of bug. For example, Claude can’t see browser-native alert modals through the Puppeteer MCP, and features relying on these modals tended to be buggier as a result.
+
+Getting up to speed
+
+With all of the above in place, every coding agent is prompted to run through a series of steps to get its bearings, some quite basic but still helpful:
+
+Run pwd to see the directory you’re working in. You’ll only be able to edit files in this directory.
+
+Read the git logs and progress files to get up to speed on what was recently worked on.
+
+Read the features list file and choose the highest-priority feature that’s not yet done to work on.
+
+This approach saves Claude some tokens in every session since it doesn’t have to figure out how to test the code. It also helps to ask the initializer agent to write an init.sh script that can run the development server, and then run through a basic end-to-end test before implementing a new feature.
+
+In the case of the claude.ai clone, this meant that the agent always started the local development server and used the Puppeteer MCP to start a new chat, send a message, and receive a response. This ensured that Claude could quickly identify if the app had been left in a broken state, and immediately fix any existing bugs. If the agent had instead started implementing a new feature, it would likely make the problem worse.
+
+Given all this, a typical session starts off with the following assistant messages:
+
+[Assistant] I'll start by getting my bearings and understanding the current state of the project.
+
+[Tool Use] <bash - pwd>
+
+[Tool Use] <read - claude-progress.txt>
+
+[Tool Use] <read - feature_list.json>
+
+[Assistant] Let me check the git log to see recent work.
+
+[Tool Use] <bash - git log --oneline -20>
+
+[Assistant] Now let me check if there's an init.sh script to restart the servers.
+
+<Starts the development server>
+
+[Assistant] Excellent! Now let me navigate to the application and verify that some fundamental features are still working.
+
+<Tests basic functionality>
+
+[Assistant] Based on my verification testing, I can see that the fundamental functionality is working well. The core chat features, theme switching, conversation loading, and error handling are all functioning correctly. Now let me review the tests.json file more comprehensively to understand what needs to be implemented next.
+
+<Starts work on a new feature>
+
+Copy
+
+Agent failure modes and solutions
+
+Problem	Initializer Agent Behavior	Coding Agent Behavior
+
+Claude declares victory on the entire project too early.	Set up a feature list file: based on the input spec, set up a structured JSON file with a list of end-to-end feature descriptions.	Read the feature list file at the beginning of a session. Choose a single feature to start working on.
+
+Claude leaves the environment in a state with bugs or undocumented progress.	An initial git repo and progress notes file is written.	Start the session by reading the progress notes file and git commit logs, and run a basic test on the development server to catch any undocumented bugs. End the session by writing a git commit and progress update.
+
+Claude marks features as done prematurely.	Set up a feature list file.	Self-verify all features. Only mark features as “passing” after careful testing.
+
+Claude has to spend time figuring out how to run the app.	Write an init.sh script that can run the development server.	Start the session by reading init.sh.
+
+Summarizing four common failure modes and solutions in long-running AI agents.
+
+Future work
+
+This research demonstrates one possible set of solutions in a long-running agent harness to enable the model to make incremental progress across many context windows. However, there remain open questions.
+
+Most notably, it’s still unclear whether a single, general-purpose coding agent performs best across contexts, or if better performance can be achieved through a multi-agent architecture. It seems reasonable that specialized agents like a testing agent, a quality assurance agent, or a code cleanup agent, could do an even better job at sub-tasks across the software development lifecycle.
+
+Additionally, this demo is optimized for full-stack web app development. A future direction is to generalize these findings to other fields. It’s likely that some or all of these lessons can be applied to the types of long-running agentic tasks required in, for example, scientific research or financial modeling.
+
+)