# Critiqor

## Docs

- [Critiqor: Runtime Intelligence Platform for AI Agents](https://critiqor-71f5274a.mintlify.app/introduction.md): Critiqor is an AI Agent Runtime Intelligence Platform that watches OpenClaw agents in real time and surfaces evidence-backed reliability diagnostics.
- [Install Critiqor: Python CLI Setup and Verification](https://critiqor-71f5274a.mintlify.app/installation.md): Install Critiqor from PyPI, verify your CLI setup, update to the latest version, and uninstall if needed. Requires Python 3.10 or newer.
- [Quickstart: Run Your First Critiqor Agent Evaluation](https://critiqor-71f5274a.mintlify.app/quickstart.md): Observe your first OpenClaw agent run with Critiqor, finalize the session, open the dashboard, and review your reliability report in five steps.
- [Runtime Observation: How Critiqor Watches Your Agent](https://critiqor-71f5274a.mintlify.app/concepts/runtime-observation.md): Critiqor records tool calls, retries, failures, and cost signals during your agent's run — giving you factual behavioral evidence beyond the final output.
- [Trust Score: Reading Reliability Signals in Critiqor](https://critiqor-71f5274a.mintlify.app/concepts/trust-score.md): The Critiqor trust score is a reliability signal based on observed runtime behavior. Learn how to read trust levels and what they mean for your agent.
- [Runs: Reviewing and Comparing Agent Reliability History](https://critiqor-71f5274a.mintlify.app/concepts/runs.md): Each finalized Critiqor session produces a run: a reliability report with trust level, diagnosis, and evidence you can review and compare over time.
- [Critiqor Dashboard: Agent Reliability Report Guide](https://critiqor-71f5274a.mintlify.app/dashboard/overview.md): The Critiqor dashboard is a local visual report generated after each observation session. Learn how to open it, navigate it, and act on what it shows.
- [Dashboard Sections: Reading Your Reliability Report](https://critiqor-71f5274a.mintlify.app/dashboard/sections.md): A guide to every section of the Critiqor dashboard — from Executive Summary to Recommendations — and how to interpret each one for your agent.
- [Observation Workflow: Start, Finalize, and Review Runs](https://critiqor-71f5274a.mintlify.app/guides/observation-workflow.md): Walk through the complete Critiqor observation workflow — start a session, use your agent, finalize the run, and review reliability results.
- [Best Practices for Getting Reliable Critiqor Evaluations](https://critiqor-71f5274a.mintlify.app/guides/best-practices.md): Get more accurate Critiqor evaluations by choosing realistic workloads, running multiple sessions, testing edge cases, and acting on recommendations.
- [Automate Deployment Gates with Critiqor Policy Checks](https://critiqor-71f5274a.mintlify.app/guides/policy-checks.md): Automate release gates with critiqor check — define trust score and hallucination risk thresholds in a policy file and block deploys that fall short.
- [Troubleshooting Critiqor Installation & Runtime Issues](https://critiqor-71f5274a.mintlify.app/troubleshooting/common-issues.md): Fix common Critiqor problems — installation failures, command not found, empty sessions, backend config errors, and dashboard display issues.
- [Critiqor FAQ: Installation, Privacy, and Usage Questions](https://critiqor-71f5274a.mintlify.app/troubleshooting/faq.md): Answers to the most common questions about Critiqor — from what it does and which frameworks it supports to data privacy and contributing.
- [Critiqor CLI Reference — All Commands and Quick Start](https://critiqor-71f5274a.mintlify.app/cli/overview.md): Complete reference for the Critiqor command-line interface. Lists every available command with purpose, syntax, and links to detailed documentation.
- [critiqor monitor openclaw — Start Runtime Observation](https://critiqor-71f5274a.mintlify.app/cli/monitor.md): critiqor monitor openclaw launches OpenClaw and begins a Critiqor observation session. Key flags: --agent-id, --difficulty-tier, --timeout, --runs-dir.
- [critiqor finalize — Complete an Observation Session](https://critiqor-71f5274a.mintlify.app/cli/finalize.md): critiqor finalize ends your observation session, generates a reliability report, and opens the dashboard. Key flags: --no-dashboard, --host, --port.
- [critiqor dashboard — Open a Run's Reliability Report](https://critiqor-71f5274a.mintlify.app/cli/dashboard.md): critiqor dashboard opens the latest or a specific run's reliability report in your browser. Pass a run ID to view it. Key flags: --runs, --host, --port.
- [critiqor runs — List Your Agent Evaluation History](https://critiqor-71f5274a.mintlify.app/cli/runs.md): critiqor runs lists all completed Critiqor observation sessions with their run ID, timestamp, trust level, and reliability summary. Key flag: --runs-dir.
- [critiqor check — Run Agent Deployment Policy Checks](https://critiqor-71f5274a.mintlify.app/cli/check.md): critiqor check validates your evaluation history against configurable thresholds. Use it to gate deployments on trust score and hallucination risk limits.
- [Critiqor Changelog: New Features, Fixes, and CLI Updates](https://critiqor-71f5274a.mintlify.app/changelog.md): Release notes for every Critiqor version — new features, improvements, bug fixes, and breaking changes that affect how you use the product.