@solidxai/core 0.1.12-beta.2 → 0.1.12-beta.3

package/docs/agent-builder/notebook-lm-prompt-for-agent-builder.md

@@ -1,136 +0,0 @@
-Use this as a copy-paste prompt for NotebookLM.
-
-:::writing{variant="document" id="73942"}
-Create a neat, professional presentation from the notes below.
-
-Audience: SolidX internal product/engineering team  
-Purpose: Explain the vision for an installable “AI Agent Builder / AI Agent Registry” module in SolidX  
-Tone: Clear, strategic, practical, product-oriented  
-Output: A slide-by-slide presentation outline with titles, bullet points, and suggested diagrams
-
-Presentation title:
-“SolidX AI Agent Builder: Metadata-Driven Enterprise Agents”
-
-Create around 10–12 slides.
-
-Structure the presentation as follows:
-
-Slide 1: Title Slide
-- SolidX AI Agent Builder / Agent Registry
-- Metadata-driven enterprise agents
-- Position this as the next evolution of SolidX workflows
-
-Slide 2: Why This Module?
-Explain the problem:
-- Enterprises need AI agents, but they also need governance, security, auditability, and workflow integration
-- Most agents today are hardcoded or isolated prototypes
-- SolidX can make agents configurable, reusable, governed, and workflow-aware
-
-Slide 3: Core Concept
-Explain:
-- AI agents become first-class SolidX metadata entities
-- Each agent is defined using metadata
-- Agent behaviour is configured, not hardcoded
-- Mini-SWE provides the autonomous runtime loop
-
-Include visual:
-Agent Definition + Skills + Tools + Knowledge Base + Policies = Runnable Enterprise Agent
-
-Slide 4: Installable SolidX Module
-Explain:
-- AI Agent Builder can be installed as a SolidX module
-- It brings its own domain model
-- It can include entities such as Agent, Skill, Tool, Knowledge Base, Policy, Agent Run, Tool Call Log
-- Configuration can be stored directly in metadata JSON
-- Runtime execution records can be stored in database tables
-
-Slide 5: Agent Configuration UI
-Explain what users can configure:
-- Agent name and description
-- System instructions
-- Allowed skills
-- Allowed tools
-- Linked knowledge bases
-- Runtime limits
-- Approval policies
-- Output schema
-
-Mention that this can be built using native SolidX CRUD screens or a custom Agent Builder UI.
-
-Slide 6: Skills Registry
-Explain:
-- Skills are reusable know-how
-- They define how the agent performs a task
-- Examples: Contract Review, Invoice Validation, Customer Escalation Handling, Code Review, Document Classification
-- A skill may contain instructions, prompt templates, examples, decision criteria, and output expectations
-
-Make clear:
-Skill = how the agent thinks/performs a task
-
-Slide 7: Tool Registry
-Explain:
-- Tools are executable capabilities
-- Examples: Send Email, Search Gmail, Query Database, Create Ticket, Read File, Call API, Search Knowledge Base
-- SolidX can provide a screen where all registered or discovered tools are visible
-- Tools may come from native SolidX APIs, internal systems, MCP servers, Composio, or custom enterprise integrations
-
-Make clear:
-Tool = what action the agent can perform
-
-Slide 8: Knowledge Base
-Explain:
-- Agents can be attached to specific knowledge bases
-- Examples: company policies, product documentation, SOPs, technical specifications, contract templates
-- Knowledge gives the agent controlled enterprise context
-- Knowledge can be attached to agents, skills, or workflows
-
-Slide 9: Agent Runtime Using Mini-SWE
-Explain:
-- Each agent runs as a Mini-SWE loop
-- When invoked, SolidX spawns an Agent Run
-- The runtime receives goal, user input, metadata, skills, tools, knowledge context, policies, and output schema
-- The loop performs: Plan → Act → Use Tool → Observe → Re-plan → Complete
-
-Include diagram:
-SolidX Agent Metadata → Mini-SWE Runtime → Tool Calls / Knowledge Search → Structured Result
-
-Slide 10: Test Interface
-Explain:
-- Once configured, users can test the agent inside SolidX
-- Default interface: chat-based console
-- Future channels: voice, WhatsApp, Slack, email, embedded app widget
-- This allows business users and developers to validate agents before attaching them to workflows
-
-Slide 11: Workflow Integration
-Explain:
-- Any SolidX workflow can include an Agent Handoff step
-- Workflow creates Agent Run
-- Agent works asynchronously
-- Agent returns result via callback/event
-- Workflow continues deterministically
-
-Include diagram:
-Workflow → Agent Handoff → Mini-SWE Agent Run → Result Callback → Workflow Continues
-
-Slide 12: Strategic Value
-Explain the positioning:
-- SolidX becomes an enterprise agent platform
-- Agents become configurable, reusable, governed, auditable, workflow-aware, tool-aware, and knowledge-aware
-- SolidX remains the control plane
-- Mini-SWE becomes the execution loop
-- Skills provide task expertise
-- Tools provide actions
-- Knowledge bases provide enterprise context
-
-End with a strong closing message:
-“SolidX AI Agent Builder turns agents from isolated prototypes into governed, reusable enterprise capabilities.”
-
-Design guidance:
-- Use clean enterprise SaaS style
-- Prefer diagrams over dense text
-- Use simple boxes and arrows
-- Use consistent terminology: Agent, Skill, Tool, Knowledge Base, Policy, Agent Run
-- Avoid hype-heavy language
-- Keep each slide concise
-- Add speaker notes for each slide explaining the idea in simple terms
-:::

package/docs/agent-builder/team-ready-note-agent-builder.md

@@ -1,305 +0,0 @@
-Here’s a team-ready note you can reuse.
-
-:::writing{variant="document" id="48291"}
-# SolidX AI Agent Builder / Agent Registry Vision
-
-## Concept
-
-The **AI Agent Builder** is a SolidX module that allows teams to define, configure, test, and deploy AI agents as first-class metadata-driven entities.
-
-The goal is to make agents configurable through SolidX rather than hardcoded in application code.
-
-Each agent is powered by a **Mini-SWE style runtime loop**, but the behaviour of the agent is controlled by SolidX metadata:
-
-```text
-Agent Definition
-+ Skills
-+ Tools
-+ Knowledge Base
-+ Policies
-+ Output Schema
-= Runnable Enterprise Agent
-```
-
----
-
-## Module Installation
-
-The AI Agent Builder can be installed as a standard SolidX module.
-
-Once installed, it brings its own domain model, such as:
-
-```text
-Agent
-Agent Skill
-Agent Tool
-Agent Knowledge Base
-Agent Policy
-Agent Run
-Agent Interaction
-Tool Call Log
-```
-
-However, the actual agent configuration can be saved directly into SolidX metadata JSON, instead of requiring every configuration detail to be stored as transactional database rows.
-
-The database can mainly store runtime records such as:
-
-```text
-Agent Run
-Conversation History
-Tool Calls
-Execution Logs
-Errors
-Audit Trail
-```
-
----
-
-## Agent Configuration UI
-
-SolidX can provide either:
-
-1. A native SolidX CRUD-style UI, or  
-2. A custom Agent Builder UI
-
-to manage agent artefacts.
-
-The user can configure:
-
-```text
-Agent name
-Agent description
-System instructions
-Allowed skills
-Allowed tools
-Linked knowledge bases
-Runtime limits
-Approval rules
-Output schema
-```
-
-Example:
-
-```text
-Customer Support Agent
-- Skill: Complaint Handling
-- Skill: Refund Policy Interpretation
-- Tool: Gmail
-- Tool: CRM
-- Knowledge Base: Support SOPs
-- Runtime: Mini-SWE
-```
-
----
-
-## Skills
-
-A skill represents reusable know-how.
-
-Examples:
-
-```text
-Contract Review
-Invoice Validation
-Customer Escalation Handling
-Code Review
-Document Classification
-```
-
-A skill may contain:
-
-```text
-Instructions
-Prompt templates
-Examples
-Decision criteria
-Expected output format
-```
-
-Skill = **how to think / how to perform a task**
-
----
-
-## Tools
-
-Tools are executable capabilities available to agents.
-
-Examples:
-
-```text
-Send Email
-Search Gmail
-Query Database
-Create Ticket
-Read File
-Call API
-Search Knowledge Base
-```
-
-Tool = **what action the agent can perform**
-
-SolidX can provide a screen where all registered/discovered tools are visible.
-
-The tool registry can include:
-
-```text
-Native SolidX tools
-Internal APIs
-MCP tools
-Composio tools
-Custom enterprise tools
-```
-
-Each tool can have metadata:
-
-```text
-Name
-Description
-Input schema
-Output schema
-Auth mode
-Approval requirement
-Allowed roles
-Provider
-```
-
----
-
-## Knowledge Base
-
-Agents can be linked to one or more knowledge bases.
-
-Examples:
-
-```text
-Company policies
-Product documentation
-Support articles
-Technical specifications
-SOPs
-Contract templates
-```
-
-This allows each agent to operate with controlled enterprise context.
-
----
-
-## Agent Runtime
-
-Each configured agent is executed as a Mini-SWE loop.
-
-When invoked, SolidX spawns an agent run and gives it:
-
-```text
-Goal
-User input
-Agent metadata
-Relevant skills
-Available tools
-Knowledge context
-Policies
-Output schema
-```
-
-The agent then runs autonomously:
-
-```text
-Plan
-Act
-Use tool
-Observe
-Re-plan
-Complete
-```
-
-The workflow engine or UI does not need to understand the internal reasoning loop.
-
-It only receives the final structured result.
-
----
-
-## Test Interface
-
-Once an agent is configured, users can test it inside SolidX.
-
-Default interface:
-
-```text
-Chat-based test console
-```
-
-Future interfaces:
-
-```text
-Voice
-WhatsApp
-Slack
-Email
-Embedded app widget
-```
-
-This allows business users and developers to validate the agent before attaching it to workflows.
-
----
-
-## Workflow Integration
-
-Any SolidX workflow can include an Agent Handoff step.
-
-Example:
-
-```text
-Workflow Step:
-Delegate document review to Document Review Agent
-```
-
-The workflow creates an Agent Run.
-
-The agent works asynchronously.
-
-When completed, it sends back a result.
-
-The workflow then continues.
-
-```text
-Workflow
-  ↓
-Agent Handoff
-  ↓
-Mini-SWE Agent Run
-  ↓
-Agent Result
-  ↓
-Workflow Continues
-```
-
----
-
-## Strategic Value
-
-This makes SolidX an enterprise agent platform, not just a workflow or low-code platform.
-
-The key advantage is that agents become:
-
-```text
-Configurable
-Reusable
-Governed
-Auditable
-Workflow-aware
-Tool-aware
-Knowledge-aware
-```
-
-SolidX remains the control plane.
-
-Mini-SWE becomes the execution loop.
-
-Tools provide actions.
-
-Skills provide task expertise.
-
-Knowledge bases provide enterprise context.
-
-Together, this creates a metadata-driven framework for building and deploying enterprise-grade AI agents.
-:::

package/docs/agent-hub-grooming.md

@@ -1,301 +0,0 @@
-# SolidX AI Agent Builder / Agent Registry Vision
-
-## Concept
-
-The **AI Agent Builder** is a SolidX module that allows teams to define, configure, test, and deploy AI agents as first-class metadata-driven entities.
-
-The goal is to make agents configurable through SolidX rather than hardcoded in application code.
-
-Each agent is powered by a **Mini-SWE style runtime loop**, but the behaviour of the agent is controlled by SolidX metadata:
-
-```text
-Agent Definition
-+ Skills
-+ Tools
-+ Knowledge Base
-+ Policies
-+ Output Schema
-= Runnable Enterprise Agent
-```
-
----
-
-## Module Installation
-
-The AI Agent Builder can be installed as a standard SolidX module.
-
-Once installed, it brings its own domain model, such as:
-
-```text
-Agent
-Agent Skill
-Agent Tool
-Agent Knowledge Base
-Agent Policy
-Agent Run
-Agent Interaction
-Tool Call Log
-```
-
-However, the actual agent configuration can be saved directly into SolidX metadata JSON, instead of requiring every configuration detail to be stored as transactional database rows.
-
-The database can mainly store runtime records such as:
-
-```text
-Agent Run
-Conversation History
-Tool Calls
-Execution Logs
-Errors
-Audit Trail
-```
-
----
-
-## Agent Configuration UI
-
-SolidX can provide either:
-
-1. A native SolidX CRUD-style UI, or  
-2. A custom Agent Builder UI
-
-to manage agent artefacts.
-
-The user can configure:
-
-```text
-Agent name
-Agent description
-System instructions
-Allowed skills
-Allowed tools
-Linked knowledge bases
-Runtime limits
-Approval rules
-Output schema
-```
-
-Example:
-
-```text
-Customer Support Agent
-- Skill: Complaint Handling
-- Skill: Refund Policy Interpretation
-- Tool: Gmail
-- Tool: CRM
-- Knowledge Base: Support SOPs
-- Runtime: Mini-SWE
-```
-
----
-
-## Skills
-
-A skill represents reusable know-how.
-
-Examples:
-
-```text
-Contract Review
-Invoice Validation
-Customer Escalation Handling
-Code Review
-Document Classification
-```
-
-A skill may contain:
-
-```text
-Instructions
-Prompt templates
-Examples
-Decision criteria
-Expected output format
-```
-
-Skill = **how to think / how to perform a task**
-
----
-
-## Tools
-
-Tools are executable capabilities available to agents.
-
-Examples:
-
-```text
-Send Email
-Search Gmail
-Query Database
-Create Ticket
-Read File
-Call API
-Search Knowledge Base
-```
-
-Tool = **what action the agent can perform**
-
-SolidX can provide a screen where all registered/discovered tools are visible.
-
-The tool registry can include:
-
-```text
-Native SolidX tools
-Internal APIs
-MCP tools
-Composio tools
-Custom enterprise tools
-```
-
-Each tool can have metadata:
-
-```text
-Name
-Description
-Input schema
-Output schema
-Auth mode
-Approval requirement
-Allowed roles
-Provider
-```
-
----
-
-## Knowledge Base
-
-Agents can be linked to one or more knowledge bases.
-
-Examples:
-
-```text
-Company policies
-Product documentation
-Support articles
-Technical specifications
-SOPs
-Contract templates
-```
-
-This allows each agent to operate with controlled enterprise context.
-
----
-
-## Agent Runtime
-
-Each configured agent is executed as a Mini-SWE loop.
-
-When invoked, SolidX spawns an agent run and gives it:
-
-```text
-Goal
-User input
-Agent metadata
-Relevant skills
-Available tools
-Knowledge context
-Policies
-Output schema
-```
-
-The agent then runs autonomously:
-
-```text
-Plan
-Act
-Use tool
-Observe
-Re-plan
-Complete
-```
-
-The workflow engine or UI does not need to understand the internal reasoning loop.
-
-It only receives the final structured result.
-
----
-
-## Test Interface
-
-Once an agent is configured, users can test it inside SolidX.
-
-Default interface:
-
-```text
-Chat-based test console
-```
-
-Future interfaces:
-
-```text
-Voice
-WhatsApp
-Slack
-Email
-Embedded app widget
-```
-
-This allows business users and developers to validate the agent before attaching it to workflows.
-
----
-
-## Workflow Integration
-
-Any SolidX workflow can include an Agent Handoff step.
-
-Example:
-
-```text
-Workflow Step:
-Delegate document review to Document Review Agent
-```
-
-The workflow creates an Agent Run.
-
-The agent works asynchronously.
-
-When completed, it sends back a result.
-
-The workflow then continues.
-
-```text
-Workflow
-  ↓
-Agent Handoff
-  ↓
-Mini-SWE Agent Run
-  ↓
-Agent Result
-  ↓
-Workflow Continues
-```
-
----
-
-## Strategic Value
-
-This makes SolidX an enterprise agent platform, not just a workflow or low-code platform.
-
-The key advantage is that agents become:
-
-```text
-Configurable
-Reusable
-Governed
-Auditable
-Workflow-aware
-Tool-aware
-Knowledge-aware
-```
-
-SolidX remains the control plane.
-
-Mini-SWE becomes the execution loop.
-
-Tools provide actions.
-
-Skills provide task expertise.
-
-Knowledge bases provide enterprise context.
-
-Together, this creates a metadata-driven framework for building and deploying enterprise-grade AI agents.