> ## Documentation Index
> Fetch the complete documentation index at: https://docs.toorow.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Agentic Daily Insights & Briefings

> How toorow synthesizes morning briefings, context events, and narrative insights for AI agents via FastMCP.

**toorow** is designed from the ground up to empower AI agents with trustworthy, audited marketing insights. The **Agentic Daily Insights** framework provides automated morning briefings, context event annotations, and narrative summaries.

***

## 1. Automated Morning Briefings

The nightly scheduler (`SCHEDULER_ENABLED=true`) triggers an automated evaluation loop at 02:00 local time:

1. **Daily Ingestion & Mart Build**: Executes datastream pulls and runs dbt models to update canonical marts.
2. **Quality & Anomaly Checks**: Evaluates data freshness, volume checks, and z-score anomaly detectors.
3. **Briefing Synthesis**: Compiles daily KPI deltas, flagged anomalies, and active business context into a structured morning briefing.

AI agents can query the latest morning briefing using the core MCP tool `get_morning_briefing(project_id)`.

***

## 2. Business Context Events

Marketing performance fluctuations rarely occur in a vacuum. toorow allows teams to register **Context Events** (e.g., website redesigns, PR announcements, price changes, ad campaign launches).

When an agent analyzes metric anomalies, toorow correlates performance shifts against registered context events, providing instant explanatory context (e.g., *"Conversions dropped 25% on July 14, coinciding with a scheduled checkout gateway migration"*).

***

## 3. FastMCP Dual-Channel Response Model

Every MCP data tool in toorow enforces a dual-channel output model (AD-1):

* **Text Channel**: A concise, structured narrative text summary (≤ 30 lines) optimized for insertion directly into the LLM context window.
* **Structured Content Channel (`structuredContent`)**: A complete JSON envelope containing raw metric arrays, data provenance, freshness timestamps, and quality alerts, rendered visually by MCP App widgets in compatible host interfaces.

***

## Next Steps & Cross-References

<CardGroup cols={2}>
  <Card title="Semantic Layer" icon="layer-group" href="/semantic-layer">
    Review canonical marts and ratio calculations supporting agent queries.
  </Card>

  <Card title="Anomaly Detection" icon="chart-line" href="/anomaly-detection-method">
    Understand z-score thresholds and severity levels for anomaly alerts.
  </Card>

  <Card title="Security Constraints" icon="shield-check" href="/constraints">
    Examine FastMCP dual-channel response rules and AD-5 tenant isolation.
  </Card>

  <Card title="Quickstart Guide" icon="rocket" href="/quickstart">
    Test MCP tool responses locally with the FastMCP dev server.
  </Card>
</CardGroup>