# Agentrail > Agentrail shows how AI agents discover, choose and use your product, and where they break. - [Introduction](https://agentrail.co/docs/index.md): Agentrail tests how AI agents find, choose and use your product, and shows you what to fix. - [Quickstart](https://agentrail.co/docs/quickstart.md): Go from a new account to a finished setup and your first agent readiness score. - [Core concepts](https://agentrail.co/docs/concepts.md): The parts of Agentrail, what each one is for, and where to read more. - [Setup](https://agentrail.co/docs/guides/setup.md): How a new workspace is created, and how Agentrail researches your company after you finish. - [Get started checklist](https://agentrail.co/docs/guides/get-started.md): See which steps are left after Setup, which apply to your product, which are done and which need attention. - [Brand Vault](https://agentrail.co/docs/guides/brand-vault.md): What Agentrail knows about your company, your products and your competitors, each fact with where it came from. - [Topics and Tags](https://agentrail.co/docs/guides/topics-and-tags.md): Name your product's capabilities with topics, and keep labels in groups with tags. - [Workflows](https://agentrail.co/docs/guides/workflows.md): Define the jobs agents can complete with your product. - [Plugin workflow tracking](https://agentrail.co/docs/guides/plugin-performance.md): Follow real workflow attempts across journeys and plugin invocations. - [Agent readiness](https://agentrail.co/docs/guides/agent-readiness.md): Scan your public website, documentation and API to see whether AI agents can find, get into, read and use them, and what to fix when they can't. - [Executions](https://agentrail.co/docs/guides/executions.md): Read exactly what a coding agent did in each run. - [Analytics](https://agentrail.co/docs/guides/analytics.md): See whether coding agents get jobs done with your product, which one they choose, and where they get stuck. - [Recommendations](https://agentrail.co/docs/guides/recommendations.md): See the problems agents hit in your product, the runs behind each one, and hand the evidence to your coding agent. - [PR checks](https://agentrail.co/docs/guides/pr-checks.md): On pull requests to your docs, SDK, CLI or MCP server, run the agent jobs you list against the pull request's real build, before you merge. - [Journeys](https://agentrail.co/docs/guides/journeys.md): Follow recorded activity across your site and pages, and inspect the evidence connecting each event. - [Alerts](https://agentrail.co/docs/guides/alerts.md): Find out when agents in your real traffic start one of your jobs and stop before finishing it, by email, in Slack and on the Alerts page. - [Install the edge](https://agentrail.co/docs/guides/journeys-edge.md): Put agentrail-edge in front of your site on Cloudflare Workers or Vercel, so every request becomes a step, including those from agents that never run JavaScript. - [Install the browser script](https://agentrail.co/docs/guides/journeys-browser.md): Add agentrail-browser to your pages with one tag, choose which calls carry the page's trace, and decide when behaviour and the fingerprint are turned on. - [Install the Node SDK](https://agentrail.co/docs/guides/journeys-node.md): agentrail-node adds your Node servers to a journey: HTTP and fetch traces, verified identity, milestones, logs and MCP calls. - [Install the Go SDK](https://agentrail.co/docs/guides/journeys-go.md): agentrail-go adds your Go servers to a journey: HTTP traces, verified identity, milestones, logs and MCP calls. - [Install the Python SDK](https://agentrail.co/docs/guides/journeys-python.md): agentrail-python adds your Python servers to a journey: HTTP traces, verified identity, milestones, logs and MCP calls, for FastAPI, Django, Flask and any ASGI or WSGI app. - [Leave out your own servers](https://agentrail.co/docs/guides/journeys-own-servers.md): Stop your own servers' calls being recorded as visitors, using a secret only your servers can send. - [What Agentrail records](https://agentrail.co/docs/guides/journeys-data.md): What the edge, the browser script and the Node, Go and Python SDKs send to Agentrail, what is hashed, and what is never recorded. - [Node SDK reference](https://agentrail.co/docs/guides/journeys-node-reference.md): Every option of agentrail-node, how to add it to an existing OpenTelemetry setup, how delivery works, and what each capture error means. - [Go SDK reference](https://agentrail.co/docs/guides/journeys-go-reference.md): Every option of agentrail-go, how to add it to an existing OpenTelemetry setup, how delivery works, and what each capture error means. - [Python SDK reference](https://agentrail.co/docs/guides/journeys-python-reference.md): Every option of agentrail-python, notes for ASGI, WSGI and worker processes, how to add it to an existing OpenTelemetry setup, how delivery works, and what each capture error means. - [Feedback](https://agentrail.co/docs/guides/feedback.md): Give AI agents a public page and address where they can tell your team what blocked or confused them in your product, without an account. - [Ask Agentrail](https://agentrail.co/docs/guides/ask-agentrail.md): Ask questions about your workspace in plain words, get short answers that link to the pages behind them, and approve any change before it is made. - [Organizations and workspaces](https://agentrail.co/docs/guides/organizations-and-workspaces.md): How an organization holds your team and a workspace holds your product, and how to create, switch, rename and leave organizations. - [People and roles](https://agentrail.co/docs/guides/people-and-roles.md): What Admins and Members can do, and how to invite people, accept an invitation, change roles and remove people. - [API introduction](https://agentrail.co/docs/api-reference/introduction.md): The public endpoints anyone can call with no account or key. - [Read the leaderboard: companies ranked by agent-readiness score, with their movement over 7 days](https://agentrail.co/docs/api-reference/leaderboard/list-leaderboard.md) - [List the leaderboard's categories](https://agentrail.co/docs/api-reference/leaderboard/list-leaderboard-categories.md) - [Read one leaderboard company by its domain: its score, grade, ranks, 7-day changes, the score, grade and rank change since its previous scan, and its current scan's summary, layers and checks](https://agentrail.co/docs/api-reference/leaderboard/get-leaderboard-company.md) - [Scan a website, MCP server or MCP App for agent readiness, or join its scan already running; optionally be emailed when it ends](https://agentrail.co/docs/api-reference/leaderboard/start-leaderboard-scan.md) - [Read a leaderboard scan as it stands: waiting, running, being scored, or ended with its score](https://agentrail.co/docs/api-reference/leaderboard/get-leaderboard-scan.md) - [Read a company's agent journeys: each task's latest one, and any running](https://agentrail.co/docs/api-reference/leaderboard/list-leaderboard-company-journeys.md) - [Run an agent journey on one of a company's tasks, or watch the one already running](https://agentrail.co/docs/api-reference/leaderboard/start-leaderboard-journey.md) - [Read an agent journey step by step: every search and page, and how each page was found](https://agentrail.co/docs/api-reference/leaderboard/get-leaderboard-journey.md) - [Read a feedback project's card: whether it accepts reports, its invitation, and where and how to send one](https://agentrail.co/docs/api-reference/feedback/get-feedback-project-card.md) - [Read the JSON Schema of a feedback project's reports](https://agentrail.co/docs/api-reference/feedback/get-feedback-report-schema.md) - [Send a feedback report: what you tried, what happened, and what was confusing or missing](https://agentrail.co/docs/api-reference/feedback/submit-feedback-report.md) - [Agentrail CLI](https://agentrail.co/docs/cli/introduction.md): Use Agentrail from a terminal or a coding agent: sign in once, then run every Agentrail tool your role can use as a command. - [Coding agents](https://agentrail.co/docs/cli/coding-agents.md): Set up Claude Code, Codex and Cursor to use Agentrail with one command, and let an agent run the CLI for you. - [Commands](https://agentrail.co/docs/cli/commands.md): The CLI's own commands, the Agentrail commands your role can use, and how inputs, workspaces and output work. - [CLI reference](https://agentrail.co/docs/cli/reference.md): The CLI's options, environment variables and files, what it tells Agentrail, and its exit codes. ## OpenAPI Specs - [openapi](https://www.agentrail.co/docs/api-reference/openapi.json?h=F25SABNX98V4V00A) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.