> ## Documentation Index
> Fetch the complete documentation index at: https://critiqor-71f5274a.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Critiqor Documentation: Runtime Intelligence for AI Agents

> Critiqor observes your AI agents during execution, captures runtime evidence, and delivers actionable reliability diagnostics through a local dashboard.

Critiqor is an AI Agent Runtime Intelligence Platform. It watches your OpenClaw agent while it runs, records what actually happened, and surfaces a reliability report you can act on — all from a single CLI command.

<CardGroup cols={2}>
  <Card title="Installation" icon="download" href="/installation">
    Install Critiqor from PyPI and verify your setup in under a minute.
  </Card>

  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Observe your first agent run and open the dashboard end-to-end.
  </Card>

  <Card title="CLI Reference" icon="terminal" href="/cli/overview">
    Every command, flag, and option — searchable and ready to copy.
  </Card>

  <Card title="Dashboard Guide" icon="chart-line" href="/dashboard/overview">
    Understand every section of the Critiqor reliability dashboard.
  </Card>
</CardGroup>

## How Critiqor works

Critiqor fits into your existing workflow without changing how you use OpenClaw. Start an observation session, use your agent as normal, then finalize to get a reliability report.

<Steps>
  <Step title="Start observing">
    Run `critiqor monitor openclaw` before you use your agent. Critiqor starts capturing runtime evidence in the background.
  </Step>

  <Step title="Use your agent normally">
    Work with OpenClaw as you usually would. Critiqor stays out of the way while recording what your agent actually does.
  </Step>

  <Step title="Finalize and review">
    Run `critiqor finalize` when you're done. Critiqor generates a reliability report and opens the dashboard automatically.
  </Step>
</Steps>

## Explore the docs

Browse the full Critiqor documentation to learn how runtime observation works, how to read your reliability reports, and how to get the most from every evaluation.

<CardGroup cols={3}>
  <Card title="Runtime Observation" icon="eye" href="/concepts/runtime-observation">
    Learn what Critiqor captures during an agent session.
  </Card>

  <Card title="Trust Score" icon="shield-check" href="/concepts/trust-score">
    Understand how to read and act on trust signals.
  </Card>

  <Card title="Observation Workflow" icon="rotate" href="/guides/observation-workflow">
    Step-by-step guide to starting, ending, and reviewing runs.
  </Card>

  <Card title="Best Practices" icon="star" href="/guides/best-practices">
    Get the most useful evaluations from every session.
  </Card>

  <Card title="Troubleshooting" icon="wrench" href="/troubleshooting/common-issues">
    Fix common installation and runtime issues fast.
  </Card>

  <Card title="FAQ" icon="circle-question" href="/troubleshooting/faq">
    Quick answers to the most common questions.
  </Card>
</CardGroup>