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

# Analytics: Measure Everything Your Assistants Do

> Feather exposes read-only analytics across sessions, tools, voice, knowledge, model routing, and more — as timeseries, breakdowns, and dashboard summaries.

Feather records rich operational data about every conversation, tool call, retrieval, and model invocation, and exposes it through a large family of read-only analytics endpoints under `/v1/analytics`. Use them to build dashboards, monitor quality and cost, and spot regressions.

All analytics endpoints are `GET`, org-scoped, and require the `analytics:read` permission. Most support a time range and return either a **timeseries**, a **breakdown**, or a rolled-up **dashboard** summary.

## Analytics domains

<CardGroup cols={2}>
  <Card title="Sessions" icon="comments">
    `/v1/analytics/sessions` — volume, channel mix, resolution and first-response time, escalation rate, turn depth.
  </Card>

  <Card title="Tools" icon="wrench">
    `/v1/analytics/tools` — invocation counts, latency, error and retry rates, reliability rankings per tool.
  </Card>

  <Card title="Voice" icon="phone">
    `/v1/analytics/voice` — call volume, answer rate, outcomes, and warm-transfer performance.
  </Card>

  <Card title="Knowledge" icon="database">
    `/v1/analytics/knowledge` — retrieval volume, top documents, ingestion and freshness metrics.
  </Card>

  <Card title="Model router" icon="microchip">
    `/v1/analytics/model-router` — cost by model, provider, assistant, and operation; latency, TTFT, fallbacks, and cache savings.
  </Card>

  <Card title="Policies" icon="shield-halved">
    `/v1/analytics/policies` — violation rates, action breakdowns, and monitor-mode rollout tracking.
  </Card>

  <Card title="Integrations & mocks" icon="plug">
    `/v1/analytics/integrations` and `/v1/analytics/mocks` — connection health, invocation success, and mock match rates.
  </Card>

  <Card title="Memory" icon="brain">
    `/v1/analytics/memory` — memory coverage and ingestion over time.
  </Card>
</CardGroup>

***

## Knowledge gaps

Beyond usage metrics, Feather clusters unanswered or low-confidence questions into **knowledge gaps** so you know what content to add. Query them under `/v1/knowledge-gaps`: a summary, the clusters themselves, per-cluster evidence and lifecycle (owner, status), and document-health signals.

***

## Using the data

The analytics surface is broad — one endpoint per metric and view — so the fastest way to find what you need is the API reference. Each endpoint documents its exact query parameters (time range, bucket granularity, filters) and response shape.

<Card title="Analytics API reference" icon="chart-bar" href="/api-reference/analytics/per-channel-comparison-of-session-volume-and-quality">
  Browse every analytics endpoint, its filters, and its response schema.
</Card>

<Note>
  Analytics endpoints are read-only reporting views. To act on data — retry a
  tool, re-run an evaluation, purge a conversation — use the corresponding
  feature API.
</Note>