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

# Observability Overview

> Inspect model requests, group conversations, measure users, and attach application context

Planck captures model activity so you can investigate failures, measure cost and latency, and understand how an application behaves in production.

<CardGroup cols={2}>
  <Card title="Properties" icon="tags" href="/features/advanced-usage/custom-properties">
    Attach environment, feature, customer, or workflow metadata to requests.
  </Card>

  <Card title="Sessions" icon="messages" href="/features/sessions">
    Group related requests into conversations or multi-step agent runs.
  </Card>

  <Card title="User Metrics" icon="users" href="/features/advanced-usage/user-metrics">
    Attribute usage, cost, and behavior to application users.
  </Card>

  <Card title="Datasets & Reports" icon="table" href="/features/datasets">
    Build reusable request sets and analyze them over time.
  </Card>

  <Card title="Scores & Feedback" icon="star" href="/features/advanced-usage/scores">
    Record automated evaluations and end-user feedback.
  </Card>

  <Card title="Webhooks" icon="webhook" href="/features/webhooks">
    Send matching Planck events to another service.
  </Card>
</CardGroup>

## A practical setup

1. Add a stable user ID and session ID to each request.
2. Add a small set of consistent properties such as `environment`, `feature`, and `workflow`.
3. Record feedback or scores against the request that produced the output.
4. Use datasets and reports for repeatable analysis.

<Tip>
  Keep property names stable and values low-cardinality when possible.
  Consistent metadata makes filtering and comparisons much easier.
</Tip>

For programmatic access, see the [Observability API](/rest/request/post-v1requestquery).