bridgekit 0.3.9__tar.gz → 0.3.11__tar.gz

{bridgekit-0.3.9 → bridgekit-0.3.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bridgekit
-Version: 0.3.9
+Version: 0.3.11
 Summary: AI tools that make you a better data scientist, not a redundant one.
 License: MIT
 Project-URL: Homepage, https://usebridgekit.com
@@ -25,6 +25,10 @@ Provides-Extra: openai
 Requires-Dist: openai>=1.0.0; extra == "openai"
 Provides-Extra: gemini
 Requires-Dist: google-generativeai>=0.3.0; extra == "gemini"
+Provides-Extra: ollama
+Requires-Dist: ollama>=0.3.0; extra == "ollama"
+Provides-Extra: openrouter
+Requires-Dist: openai>=1.0.0; extra == "openrouter"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-mock>=3.0.0; extra == "dev"
@@ -87,6 +91,18 @@ pip install bridgekit[gemini]
 export GOOGLE_API_KEY=your_key_here
 ```
 
+**Ollama (local models, free, no API key):**
+```bash
+pip install bridgekit[ollama]
+# Make sure Ollama is running locally: https://ollama.com
+```
+
+**OpenRouter (free and paid models via one API):**
+```bash
+pip install bridgekit[openrouter]
+export OPENROUTER_API_KEY=your_key_here
+```
+
 ---
 
 ## Getting Started
@@ -398,7 +414,7 @@ willing to commit to — and what's your confidence interval on that estimate?"
 
 ## Tool #5: Compare
 
-Run the same tool through two providers and see both outputs side by side. Useful for evaluating which model works best for your use case — as a one-liner.
+Run the same tool through two providers and see both outputs side by side. A synthesis summary at the top highlights where the models agreed, where they differed in severity, and which gave more actionable feedback — so you get the key insight without reading both outputs in full. Useful for evaluating which model works best for your use case — as a one-liner.
 
 ```python
 from bridgekit import compare
@@ -437,6 +453,16 @@ print(compare(text, providers=["anthropic", "gemini"]))
 BRIDGEKIT COMPARE: EVALUATE
 ─────────────────────────────────────────
 
+SUMMARY
+─────────────────────────────────────────
+Both outputs rated Clarity as STRONG. They diverged on severity: Anthropic
+rated Statistical Rigor as MISSING (harsher) while OpenAI called it NEEDS WORK.
+Anthropic gave more specific feedback — naming the correlation-vs-causation
+problem explicitly and suggesting concrete fixes. OpenAI's feedback stayed
+more generic. Anthropic's bottom line targets the core analytical flaw;
+OpenAI's restates the statistical point only.
+
+
 ANTHROPIC  claude-opus-4-8
 ─────────────────────────────────────────
 BRIDGEKIT ANALYSIS REVIEW
@@ -458,13 +484,67 @@ BRIDGEKIT ANALYSIS REVIEW
 ...
 ```
 
-Both providers are called in parallel, so the total wait time is the slower of the two — not the sum.
+Both providers are called in parallel, so the total wait time is the slower of the two — not the sum. The synthesis summary is a third sequential call made after both outputs are ready.
+
+---
+
+## Tool #6: Summarize
+
+Turn a long analysis writeup, notebook, or report into a short executive summary — the gap between doing the analysis and communicating it to people who won't read the whole thing.
+
+```python
+from bridgekit import summarize
+
+text = """
+I analyzed 90 days of user behavior data to understand what drives subscription
+upgrades. Users who engaged with the reporting feature within their first week
+were 3x more likely to upgrade within 30 days. Sample size was 1,200 users
+across two acquisition channels, with consistent results in both. I recommend
+we prioritize onboarding users to reporting as a growth lever.
+"""
+
+# Default — general business audience
+print(summarize(text))
+
+# Or specify an audience
+print(summarize(text, audience="VP of Marketing"))
+print(summarize(text, audience="board"))
+
+# Override for longer summaries
+print(summarize(text, max_tokens=2048))
+```
+
+**Output:**
+```
+BRIDGEKIT SUMMARY
+─────────────────────────────────────────
+AUDIENCE: VP of Marketing
+
+KEY TAKEAWAY
+Getting users into the reporting feature in their first week is our strongest
+predictor of paid upgrades — users who engage with it are 3x more likely to
+convert within 30 days.
+
+WHAT WE FOUND
+- Early reporting engagement (week 1) drives 3x higher upgrade rates within 30 days
+- Finding holds across both acquisition channels, suggesting it's a genuine
+  behavior pattern, not channel-specific
+- Analyzed 1,200 users over 90 days with sufficient scale to trust the result
+
+SO WHAT
+We should redesign onboarding to get users to reporting faster. This is a
+high-confidence growth lever worth testing immediately.
+
+─────────────────────────────────────────
+```
+
+`audience`, `provider`, `model`, `system_prompt`, and `max_tokens` are all optional — the more specific the audience, the more tailored the summary.
 
 ---
 
 ## Multi-Provider Support
 
-Bridgekit now supports multiple AI providers so you're not locked into one API. You can use Anthropic, OpenAI, or Google Gemini models with any tool.
+Bridgekit now supports multiple AI providers so you're not locked into one API. You can use Anthropic, OpenAI, Google Gemini, local models via Ollama, or any model on OpenRouter with any tool.
 
 **Using different providers:**
 
@@ -477,27 +557,42 @@ print(evaluate("Your analysis here", provider="openai"))
 # Use Google Gemini (default model: gemini-1.5-pro)
 print(plan("Your question here", provider="gemini"))
 
+# Use a local model via Ollama - free, private, no API key (default model: llama3.2)
+print(evaluate("Your analysis here", provider="ollama"))
+
+# Use OpenRouter to access a wide range of models, including free tiers
+print(evaluate("Your analysis here", provider="openrouter", model="deepseek/deepseek-v4-flash-0731:free"))
+
 # Use specific model
 print(redteam("Your analysis here", model="gpt-4-turbo"))
 print(ask("Your question here", source="reports/", model="claude-3-opus-20240229"))
 ```
 
+**Ollama setup:** install and start [Ollama](https://ollama.com) locally, then pull a model (e.g. `ollama pull llama3.2`). By default Bridgekit connects to `http://localhost:11434`; set `OLLAMA_HOST` to point at a different host.
+
 **Provider auto-detection:**
 Bridgekit automatically detects the provider from model names:
 - Models starting with "claude" → Anthropic
 - Models starting with "gpt" → OpenAI  
 - Models starting with "gemini" → Google Gemini
+- Model names containing "/" (e.g. `deepseek/deepseek-v4-flash-0731:free`) → OpenRouter
+- Common local model families (e.g. "llama", "mistral", "mixtral", "gemma", "phi", "qwen") → Ollama
 
 **Default models by provider:**
 - Anthropic: `claude-opus-4-8`
 - OpenAI: `gpt-4o`
 - Gemini: `gemini-1.5-pro`
+- Ollama: `llama3.2`
+- OpenRouter: `deepseek/deepseek-v4-flash-0731:free`
+
+> **Note:** OpenRouter's free-tier model lineup rotates over time. Check the current list at [openrouter.ai/models?max_price=0](https://openrouter.ai/models?max_price=0) if a `:free` model stops working, and pass `model=` explicitly with whichever slug is currently free.
 
 All tools support the same `provider` and `model` parameters:
 - `evaluate(text, provider=None, model=None, system_prompt=None)`
 - `plan(question, provider=None, model=None, ..., system_prompt=None)`
 - `ask(question, provider=None, model=None, ..., system_prompt=None)`
 - `redteam(text, provider=None, model=None, ..., system_prompt=None)`
+- `summarize(text, provider=None, model=None, ..., system_prompt=None)`
 
 ---
 
@@ -506,7 +601,7 @@ All tools support the same `provider` and `model` parameters:
 Every tool accepts an optional `system_prompt` parameter to override the default persona. Use this to adapt the tone or focus to a specific domain without changing anything else.
 
 ```python
-from bridgekit import evaluate, plan, ask, redteam
+from bridgekit import evaluate, plan, ask, redteam, summarize
 
 # Narrow the reviewer to a specific domain
 print(evaluate("my analysis", system_prompt="You are a skeptical PhD statistician focused only on methodology"))
@@ -519,6 +614,9 @@ print(redteam("my analysis", system_prompt="You are a hostile regulator looking
 
 # Change the answering style for ask
 print(ask("my question", text="...", system_prompt="You are a financial analyst. Answer only in terms of revenue impact."))
+
+# Replace the summarizer persona entirely
+print(summarize("my analysis", system_prompt="You are a data journalist writing a one-paragraph news brief."))
 ```
 
 When `system_prompt` is not provided, each tool uses its built-in default — existing behavior is unchanged.

{bridgekit-0.3.9 → bridgekit-0.3.11}/README.md

@@ -55,6 +55,18 @@ pip install bridgekit[gemini]
 export GOOGLE_API_KEY=your_key_here
 ```
 
+**Ollama (local models, free, no API key):**
+```bash
+pip install bridgekit[ollama]
+# Make sure Ollama is running locally: https://ollama.com
+```
+
+**OpenRouter (free and paid models via one API):**
+```bash
+pip install bridgekit[openrouter]
+export OPENROUTER_API_KEY=your_key_here
+```
+
 ---
 
 ## Getting Started
@@ -366,7 +378,7 @@ willing to commit to — and what's your confidence interval on that estimate?"
 
 ## Tool #5: Compare
 
-Run the same tool through two providers and see both outputs side by side. Useful for evaluating which model works best for your use case — as a one-liner.
+Run the same tool through two providers and see both outputs side by side. A synthesis summary at the top highlights where the models agreed, where they differed in severity, and which gave more actionable feedback — so you get the key insight without reading both outputs in full. Useful for evaluating which model works best for your use case — as a one-liner.
 
 ```python
 from bridgekit import compare
@@ -405,6 +417,16 @@ print(compare(text, providers=["anthropic", "gemini"]))
 BRIDGEKIT COMPARE: EVALUATE
 ─────────────────────────────────────────
 
+SUMMARY
+─────────────────────────────────────────
+Both outputs rated Clarity as STRONG. They diverged on severity: Anthropic
+rated Statistical Rigor as MISSING (harsher) while OpenAI called it NEEDS WORK.
+Anthropic gave more specific feedback — naming the correlation-vs-causation
+problem explicitly and suggesting concrete fixes. OpenAI's feedback stayed
+more generic. Anthropic's bottom line targets the core analytical flaw;
+OpenAI's restates the statistical point only.
+
+
 ANTHROPIC  claude-opus-4-8
 ─────────────────────────────────────────
 BRIDGEKIT ANALYSIS REVIEW
@@ -426,13 +448,67 @@ BRIDGEKIT ANALYSIS REVIEW
 ...
 ```
 
-Both providers are called in parallel, so the total wait time is the slower of the two — not the sum.
+Both providers are called in parallel, so the total wait time is the slower of the two — not the sum. The synthesis summary is a third sequential call made after both outputs are ready.
+
+---
+
+## Tool #6: Summarize
+
+Turn a long analysis writeup, notebook, or report into a short executive summary — the gap between doing the analysis and communicating it to people who won't read the whole thing.
+
+```python
+from bridgekit import summarize
+
+text = """
+I analyzed 90 days of user behavior data to understand what drives subscription
+upgrades. Users who engaged with the reporting feature within their first week
+were 3x more likely to upgrade within 30 days. Sample size was 1,200 users
+across two acquisition channels, with consistent results in both. I recommend
+we prioritize onboarding users to reporting as a growth lever.
+"""
+
+# Default — general business audience
+print(summarize(text))
+
+# Or specify an audience
+print(summarize(text, audience="VP of Marketing"))
+print(summarize(text, audience="board"))
+
+# Override for longer summaries
+print(summarize(text, max_tokens=2048))
+```
+
+**Output:**
+```
+BRIDGEKIT SUMMARY
+─────────────────────────────────────────
+AUDIENCE: VP of Marketing
+
+KEY TAKEAWAY
+Getting users into the reporting feature in their first week is our strongest
+predictor of paid upgrades — users who engage with it are 3x more likely to
+convert within 30 days.
+
+WHAT WE FOUND
+- Early reporting engagement (week 1) drives 3x higher upgrade rates within 30 days
+- Finding holds across both acquisition channels, suggesting it's a genuine
+  behavior pattern, not channel-specific
+- Analyzed 1,200 users over 90 days with sufficient scale to trust the result
+
+SO WHAT
+We should redesign onboarding to get users to reporting faster. This is a
+high-confidence growth lever worth testing immediately.
+
+─────────────────────────────────────────
+```
+
+`audience`, `provider`, `model`, `system_prompt`, and `max_tokens` are all optional — the more specific the audience, the more tailored the summary.
 
 ---
 
 ## Multi-Provider Support
 
-Bridgekit now supports multiple AI providers so you're not locked into one API. You can use Anthropic, OpenAI, or Google Gemini models with any tool.
+Bridgekit now supports multiple AI providers so you're not locked into one API. You can use Anthropic, OpenAI, Google Gemini, local models via Ollama, or any model on OpenRouter with any tool.
 
 **Using different providers:**
 
@@ -445,27 +521,42 @@ print(evaluate("Your analysis here", provider="openai"))
 # Use Google Gemini (default model: gemini-1.5-pro)
 print(plan("Your question here", provider="gemini"))
 
+# Use a local model via Ollama - free, private, no API key (default model: llama3.2)
+print(evaluate("Your analysis here", provider="ollama"))
+
+# Use OpenRouter to access a wide range of models, including free tiers
+print(evaluate("Your analysis here", provider="openrouter", model="deepseek/deepseek-v4-flash-0731:free"))
+
 # Use specific model
 print(redteam("Your analysis here", model="gpt-4-turbo"))
 print(ask("Your question here", source="reports/", model="claude-3-opus-20240229"))
 ```
 
+**Ollama setup:** install and start [Ollama](https://ollama.com) locally, then pull a model (e.g. `ollama pull llama3.2`). By default Bridgekit connects to `http://localhost:11434`; set `OLLAMA_HOST` to point at a different host.
+
 **Provider auto-detection:**
 Bridgekit automatically detects the provider from model names:
 - Models starting with "claude" → Anthropic
 - Models starting with "gpt" → OpenAI  
 - Models starting with "gemini" → Google Gemini
+- Model names containing "/" (e.g. `deepseek/deepseek-v4-flash-0731:free`) → OpenRouter
+- Common local model families (e.g. "llama", "mistral", "mixtral", "gemma", "phi", "qwen") → Ollama
 
 **Default models by provider:**
 - Anthropic: `claude-opus-4-8`
 - OpenAI: `gpt-4o`
 - Gemini: `gemini-1.5-pro`
+- Ollama: `llama3.2`
+- OpenRouter: `deepseek/deepseek-v4-flash-0731:free`
+
+> **Note:** OpenRouter's free-tier model lineup rotates over time. Check the current list at [openrouter.ai/models?max_price=0](https://openrouter.ai/models?max_price=0) if a `:free` model stops working, and pass `model=` explicitly with whichever slug is currently free.
 
 All tools support the same `provider` and `model` parameters:
 - `evaluate(text, provider=None, model=None, system_prompt=None)`
 - `plan(question, provider=None, model=None, ..., system_prompt=None)`
 - `ask(question, provider=None, model=None, ..., system_prompt=None)`
 - `redteam(text, provider=None, model=None, ..., system_prompt=None)`
+- `summarize(text, provider=None, model=None, ..., system_prompt=None)`
 
 ---
 
@@ -474,7 +565,7 @@ All tools support the same `provider` and `model` parameters:
 Every tool accepts an optional `system_prompt` parameter to override the default persona. Use this to adapt the tone or focus to a specific domain without changing anything else.
 
 ```python
-from bridgekit import evaluate, plan, ask, redteam
+from bridgekit import evaluate, plan, ask, redteam, summarize
 
 # Narrow the reviewer to a specific domain
 print(evaluate("my analysis", system_prompt="You are a skeptical PhD statistician focused only on methodology"))
@@ -487,6 +578,9 @@ print(redteam("my analysis", system_prompt="You are a hostile regulator looking
 
 # Change the answering style for ask
 print(ask("my question", text="...", system_prompt="You are a financial analyst. Answer only in terms of revenue impact."))
+
+# Replace the summarizer persona entirely
+print(summarize("my analysis", system_prompt="You are a data journalist writing a one-paragraph news brief."))
 ```
 
 When `system_prompt` is not provided, each tool uses its built-in default — existing behavior is unchanged.

{bridgekit-0.3.9 → bridgekit-0.3.11}/bridgekit/__init__.py

@@ -3,6 +3,7 @@ from .search import ask
 from .planner import plan
 from .redteam import redteam
 from .compare import compare
+from .summarize import summarize
 
-__version__ = "0.3.9"
-__all__ = ["evaluate", "ask", "plan", "redteam", "compare"]
+__version__ = "0.3.10"
+__all__ = ["evaluate", "ask", "plan", "redteam", "compare", "summarize"]

{bridgekit-0.3.9 → bridgekit-0.3.11}/bridgekit/config.py

@@ -7,25 +7,39 @@ class Provider(Enum):
     ANTHROPIC = "anthropic"
     OPENAI = "openai"
     GEMINI = "gemini"
+    OLLAMA = "ollama"
+    OPENROUTER = "openrouter"
 
 
 # Default models for each provider
 DEFAULT_MODELS = {
     Provider.ANTHROPIC: "claude-opus-4-8",
     Provider.OPENAI: "gpt-4o",
-    Provider.GEMINI: "gemini-1.5-pro"
+    Provider.GEMINI: "gemini-1.5-pro",
+    Provider.OLLAMA: "llama3.2",
+    Provider.OPENROUTER: "deepseek/deepseek-v4-flash-0731:free",
 }
 
 # Legacy support
 DEFAULT_MODEL = DEFAULT_MODELS[Provider.ANTHROPIC]
 
+# Common local model family names served by Ollama. Used to infer the
+# provider from a bare model name when no explicit provider is given.
+OLLAMA_MODEL_PREFIXES = (
+    "llama", "mistral", "mixtral", "gemma", "phi", "qwen",
+    "codellama", "vicuna", "deepseek", "tinyllama",
+)
 
-def require_api_key(provider: Provider = Provider.ANTHROPIC) -> str:
+
+def require_api_key(provider: Provider = Provider.ANTHROPIC) -> Optional[str]:
     """Return the API key for the specified provider from the environment, or raise a clear error.
 
     Each Bridgekit tool calls this before constructing a client so
     users get the same friendly message instead of whatever the SDK surfaces
     when the key is missing.
+
+    Ollama runs locally and doesn't use an API key, so this returns None
+    for that provider instead of raising.
     """
     if provider == Provider.ANTHROPIC:
         api_key = os.environ.get("ANTHROPIC_API_KEY")
@@ -48,6 +62,15 @@ def require_api_key(provider: Provider = Provider.ANTHROPIC) -> str:
                 "GOOGLE_API_KEY not found. Set it with: export GOOGLE_API_KEY=your_key_here"
             )
         return api_key
+    elif provider == Provider.OLLAMA:
+        return None
+    elif provider == Provider.OPENROUTER:
+        api_key = os.environ.get("OPENROUTER_API_KEY")
+        if not api_key:
+            raise EnvironmentError(
+                "OPENROUTER_API_KEY not found. Set it with: export OPENROUTER_API_KEY=your_key_here"
+            )
+        return api_key
     else:
         raise ValueError(f"Unsupported provider: {provider}")
 
@@ -73,7 +96,13 @@ def parse_provider(provider: Optional[str] = None, model: Optional[str] = None)
             return Provider.OPENAI
         elif model.startswith("gemini"):
             return Provider.GEMINI
-    
+        elif "/" in model:
+            # OpenRouter model names use a "vendor/model" format,
+            # e.g. "deepseek/deepseek-v4-flash-0731:free"
+            return Provider.OPENROUTER
+        elif model.startswith(OLLAMA_MODEL_PREFIXES):
+            return Provider.OLLAMA
+
     # Default to Anthropic for backward compatibility
     return Provider.ANTHROPIC
 

{bridgekit-0.3.9 → bridgekit-0.3.11}/bridgekit/providers.py

@@ -1,5 +1,6 @@
 """Provider client factory for Bridgekit multi-provider support."""
 
+import os
 from typing import Union, Dict, Any, List
 from .config import Provider, require_api_key, get_default_model
 
@@ -39,11 +40,14 @@ class AnthropicClient(BaseProviderClient):
 
 class OpenAIClient(BaseProviderClient):
     """OpenAI provider client."""
-    
-    def __init__(self, api_key: str):
+
+    def __init__(self, api_key: str, base_url: str = None):
         super().__init__(api_key)
         import openai
-        self.client = openai.OpenAI(api_key=api_key)
+        if base_url:
+            self.client = openai.OpenAI(api_key=api_key, base_url=base_url)
+        else:
+            self.client = openai.OpenAI(api_key=api_key)
     
     def create_message(self, system_prompt: str, user_message: str, model: str, max_tokens: int = 1024) -> str:
         """Create a message using OpenAI's API."""
@@ -86,6 +90,35 @@ class GeminiClient(BaseProviderClient):
         return response.text
 
 
+class OllamaClient(BaseProviderClient):
+    """Ollama provider client for locally-hosted models. No API key required."""
+
+    def __init__(self, api_key: str = None):
+        super().__init__(api_key)
+        import ollama
+        host = os.environ.get("OLLAMA_HOST", "http://localhost:11434")
+        self.client = ollama.Client(host=host)
+
+    def create_message(self, system_prompt: str, user_message: str, model: str, max_tokens: int = 1024) -> str:
+        """Create a message using a locally-hosted Ollama model."""
+        response = self.client.chat(
+            model=model,
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_message}
+            ],
+            options={"num_predict": max_tokens}
+        )
+        return response["message"]["content"]
+
+
+class OpenRouterClient(OpenAIClient):
+    """OpenRouter provider client. OpenAI-compatible API routing to many models, including free tiers."""
+
+    def __init__(self, api_key: str):
+        super().__init__(api_key, base_url="https://openrouter.ai/api/v1")
+
+
 def create_client(provider: Provider, model: str = None) -> BaseProviderClient:
     """Create a client for the specified provider."""
     if model is None:
@@ -99,6 +132,10 @@ def create_client(provider: Provider, model: str = None) -> BaseProviderClient:
         return OpenAIClient(api_key)
     elif provider == Provider.GEMINI:
         return GeminiClient(api_key)
+    elif provider == Provider.OLLAMA:
+        return OllamaClient(api_key)
+    elif provider == Provider.OPENROUTER:
+        return OpenRouterClient(api_key)
     else:
         raise ValueError(f"Unsupported provider: {provider}")
 

bridgekit-0.3.11/bridgekit/summarize.py

@@ -0,0 +1,72 @@
+from .config import DEFAULT_MODEL, parse_provider, get_default_model
+from .providers import create_message
+
+DEFAULT_AUDIENCE = "a general business audience with no technical or data science background"
+
+SYSTEM_PROMPT_TEMPLATE = """You are a senior data scientist preparing an executive summary of a technical analysis for {audience}.
+
+Your job is to translate technical detail into what matters for decision-making. Cut jargon, cut methodology detail unless it's essential to trust the conclusion, and lead with the takeaway. Write for someone who will skim this in 30 seconds.
+
+Format your response exactly like this:
+
+BRIDGEKIT SUMMARY
+─────────────────────────────────────────
+AUDIENCE: {audience_label}
+
+KEY TAKEAWAY
+[1-2 sentences: the single most important finding or recommendation]
+
+WHAT WE FOUND
+[3-5 bullet points of the supporting findings, in plain language]
+
+SO WHAT
+[1-2 sentences on the business implication or recommended next step]
+
+─────────────────────────────────────────
+"""
+
+
+def summarize(text: str, audience: str = None, provider: str = None, model: str = None, system_prompt: str = None, max_tokens: int = 1024) -> str:
+    """
+    Turn a long analysis, notebook, or report into a short executive summary.
+
+    Args:
+        text:          The long-form analysis writeup, notebook output, or report as a plain string.
+        audience:      Optional. Who the summary is for (e.g. "VP of Marketing", "board",
+                       "engineering team"). Defaults to a general business audience.
+        provider:      Optional. The AI provider to use ("anthropic", "openai", "gemini").
+                       If not specified, defaults to "anthropic" or infers from model.
+        model:         Optional. The specific model to use. If not specified, uses the provider's default.
+        system_prompt: Optional. A custom system prompt to fully override the default summarizer persona.
+                       When provided, the audience parameter is ignored.
+        max_tokens:    Optional. Maximum tokens in the response. Defaults to 1024.
+
+    Returns:
+        A short executive summary covering the key takeaway, supporting findings,
+        and the business implication.
+    """
+    if not text or not text.strip():
+        raise ValueError("Text cannot be empty.")
+
+    # Parse provider and determine model
+    provider_enum = parse_provider(provider, model)
+    if model is None:
+        model = get_default_model(provider_enum)
+
+    if system_prompt is None:
+        audience_label = audience if audience else "General Business Audience"
+        audience_desc = audience if audience else DEFAULT_AUDIENCE
+        system_prompt = SYSTEM_PROMPT_TEMPLATE.format(
+            audience=audience_desc,
+            audience_label=audience_label
+        )
+
+    user_message = f"Summarize this analysis:\n\n{text}"
+
+    return create_message(
+        provider=provider_enum,
+        system_prompt=system_prompt,
+        user_message=user_message,
+        model=model,
+        max_tokens=max_tokens
+    )