diff --git a/.env.example b/.env.example
new file mode 100644
index 0000000..fb3f1b6
--- /dev/null
+++ b/.env.example
@@ -0,0 +1,3 @@
+LLM_API_URL=https://litellm-notrack.app.monadical.io
+LLM_MODEL=GLM-4.5-Air-FP8-dev
+LLM_API_KEY=xxxxx
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..4c49bd7
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+.env
diff --git a/README.md b/README.md
index 2ea6d54..6b493eb 100644
--- a/README.md
+++ b/README.md
@@ -33,6 +33,14 @@ The goal is to use [opencode](https://opencode.ai) (or any LLM-powered coding to
 
 Replace `xxxxx` with your actual LiteLLM API key.
 
+4. **(Optional) LLM filtering in workflows** — if your workflows need to classify or score entities via an LLM, copy `.env.example` to `.env` and fill in your key:
+
+```bash
+cp .env.example .env
+```
+
+The `workflows/lib` module provides an `llm_call` helper (using [mirascope](https://mirascope.io)) for structured LLM calls — see Pattern 5 in `docs/notebook-patterns.md`.
+
 ## Quickstart
 
 1. Run `opencode` from the project root
@@ -60,11 +68,15 @@ It also includes API base URLs, a translation table mapping natural-language que
 ```
 internalai-agent/
 ├── AGENTS.md                        # LLM agent routing guide (entry point)
+├── .env.example                     # LLM credentials template
 ├── docs/
 │   ├── company-context.md           # Monadical org, tools, key concepts
 │   ├── contactdb-api.md             # ContactDB REST API reference
 │   ├── dataindex-api.md             # DataIndex REST API reference
 │   ├── connectors-and-sources.md    # Connector → entity type mappings
 │   └── notebook-patterns.md         # Marimo notebook templates and patterns
-└── workflows/                       # Generated analysis notebooks go here
+└── workflows/
+    └── lib/                         # Shared helpers for notebooks
+        ├── __init__.py
+        └── llm.py                   # llm_call() — structured LLM calls via mirascope
 ```
diff --git a/docs/notebook-patterns.md b/docs/notebook-patterns.md
index e224fb3..e5611c1 100644
--- a/docs/notebook-patterns.md
+++ b/docs/notebook-patterns.md
@@ -425,6 +425,89 @@ def display_timeline(timeline_df):
     timeline_df
 ```
 
+## Pattern 5: LLM Filtering with `lib.llm`
+
+When you need to classify, score, or extract structured information from each entity (e.g. "is this meeting about project X?", "rate the relevance of this email"), use the `llm_call` helper from `workflows/lib`. It sends each item to an LLM and parses the response into a typed Pydantic model.
+
+**Prerequisites:** Copy `.env.example` to `.env` and fill in your `LLM_API_KEY`. Add `mirascope` and `pydantic` to the notebook's PEP 723 dependencies.
+
+```python
+# /// script
+# requires-python = ">=3.12"
+# dependencies = [
+#     "marimo",
+#     "httpx",
+#     "polars",
+#     "mirascope",
+#     "pydantic",
+# ]
+# ///
+```
+
+### Setup cell — import `llm_call`
+
+```python
+@app.cell
+def setup():
+    import httpx
+    import marimo as mo
+    import polars as pl
+    from lib.llm import llm_call
+    client = httpx.Client(timeout=30)
+    return (client, llm_call, mo, pl,)
+```
+
+### Define a response model
+
+Create a Pydantic model that describes the structured output you want from the LLM:
+
+```python
+@app.cell
+def models():
+    from pydantic import BaseModel
+
+    class RelevanceScore(BaseModel):
+        relevant: bool
+        reason: str
+        score: int  # 0-10
+
+    return (RelevanceScore,)
+```
+
+### Filter entities through the LLM
+
+Iterate over fetched entities and call `llm_call` for each one. Since `llm_call` is async, use `asyncio.gather` to process items concurrently:
+
+```python
+@app.cell
+async def llm_filter(meetings, llm_call, RelevanceScore, pl, mo):
+    import asyncio
+
+    _topic = "Greyhaven"
+
+    async def _score(meeting):
+        _text = meeting.get("summary") or meeting.get("title") or ""
+        _result = await llm_call(
+            prompt=f"Is this meeting about '{_topic}'?\n\nMeeting: {_text}",
+            response_model=RelevanceScore,
+            system_prompt="Score the relevance of this meeting to the given topic. Set relevant=true if score >= 5.",
+        )
+        return {**meeting, "llm_relevant": _result.relevant, "llm_reason": _result.reason, "llm_score": _result.score}
+
+    scored_meetings = await asyncio.gather(*[_score(_m) for _m in meetings])
+    relevant_meetings = [_m for _m in scored_meetings if _m["llm_relevant"]]
+
+    mo.md(f"**LLM filter:** {len(relevant_meetings)}/{len(meetings)} meetings relevant to '{_topic}'")
+    return (relevant_meetings,)
+```
+
+### Tips for LLM filtering
+
+- **Keep prompts short** — only include the fields the LLM needs (title, summary, snippet), not the entire raw entity.
+- **Use structured output** — always pass a `response_model` so you get typed fields back, not free-text.
+- **Batch wisely** — `asyncio.gather` sends all requests concurrently. For large datasets (100+ items), process in chunks to avoid rate limits.
+- **Cache results** — LLM calls are slow and cost money. If iterating on a notebook, consider storing scored results in a cell variable so you don't re-score on every edit.
+
 ## Do / Don't — Quick Reference for LLM Agents
 
 When generating marimo notebooks, follow these rules strictly. Violations cause `MultipleDefinitionError` at runtime.
diff --git a/workflows/lib/__init__.py b/workflows/lib/__init__.py
new file mode 100644
index 0000000..94b72a0
--- /dev/null
+++ b/workflows/lib/__init__.py
@@ -0,0 +1,5 @@
+"""Library modules for contact analysis workbooks."""
+
+from lib.llm import llm_call
+
+__all__ = ["llm_call"]
diff --git a/workflows/lib/llm.py b/workflows/lib/llm.py
new file mode 100644
index 0000000..3cfe91d
--- /dev/null
+++ b/workflows/lib/llm.py
@@ -0,0 +1,51 @@
+"""Simple LLM helper for workbooks using Mirascope."""
+
+import os
+from typing import TypeVar
+
+from mirascope.core import Messages, openai
+from pydantic import BaseModel
+
+T = TypeVar("T", bound=BaseModel)
+
+# Configure from environment (defaults match .env.example)
+_api_key = os.getenv("LLM_API_KEY", "")
+_base_url = os.getenv("LLM_API_URL", "https://litellm-notrack.app.monadical.io")
+_model = os.getenv("LLM_MODEL", "GLM-4.5-Air-FP8-dev")
+
+if _api_key:
+    os.environ["OPENAI_API_KEY"] = _api_key
+if _base_url:
+    base = _base_url.rstrip("/")
+    os.environ["OPENAI_BASE_URL"] = base if base.endswith("/v1") else f"{base}/v1"
+
+
+async def llm_call(
+    prompt: str,
+    response_model: type[T],
+    system_prompt: str = "You are a helpful assistant.",
+    model: str | None = None,
+) -> T:
+    """Make a structured LLM call.
+
+    Args:
+        prompt: The user prompt
+        response_model: Pydantic model for structured output
+        system_prompt: System instructions
+        model: Override the default model
+
+    Returns:
+        Parsed response matching the response_model schema
+    """
+    use_model = model or _model
+
+    @openai.call(model=use_model, response_model=response_model)
+    async def _call(sys: str, usr: str) -> openai.OpenAIDynamicConfig:
+        return {
+            "messages": [
+                Messages.System(sys),
+                Messages.User(usr),
+            ]
+        }
+
+    return await _call(system_prompt, prompt)