Getting started with verifAIed
verifAIed checks the work your coding agent says it finished: that the code it wrote is tested, and that the feature works in a real browser.
Prefer to watch? The tutorial video shows the everyday workflow from start to finish, then walks through setting up an account.
Your coding agent can answer questions about verifAIed. Once it is connected, ask it how something works: it reads this documentation through the
docs tool. See MCP tools.What verifAIed does
Your agent says it is done. verifAIed answers the two questions that leaves: what did it build, and is it really finished?
- Your agent writes the code and its tests, then uploads the test coverage to verifAIed.
- It records browser tests: flows through your running app, with a check after each step and a video of the result.
- It asks verifAIed
check_done. The answer is done, or a list of gaps, each with the next thing to do. - It fixes the gaps and asks again, until the answer is done.
- You open the branch and watch the videos, instead of checking the work by hand.
Build a feature with your agent walks through that loop once. New here? Start with Set up.
What verifAIed works with
- Repositories on GitHub. verifAIed connects through a GitHub App; other hosts, such as GitLab and Bitbucket, are not supported.
- Unit coverage for Python, from pytest with pytest-cov, and for JavaScript and TypeScript, from vitest with its Istanbul provider.
- Browser tests for web apps, recorded and replayed with Playwright.
- Claude Code, Codex, Cursor, Antigravity, and any other coding agent that can connect to an MCP server.
In this documentation
Get started
- Set up: Connect GitHub, connect your coding agent and set up a repository.
Everyday workflow
- Build a feature with your agent: The loop your agent runs: write, test, upload, check, fix, until verifAIed says done.
- Repositories and branches: What the repository page shows and what each status means.
- Unit coverage: What is tested, function by function, and prompts that close the gaps.
- Definition of done: How verifAIed decides a branch is finished, and how to change the rules.
Browser tests
- What browser tests are: Recorded flows through your running app, replayed with video.
- Record a test: Start the studio, name a test and click through the flow.
- Studio tools: Pick an element, add actions and checks, run a script, or describe steps to the Assistant.
- Record with your agent: Let your coding agent record and prove a flow by itself.
- Edit a test: Change a check, redo a test from any step, rename it or chain it after another.
- Run tests: Run from the web, the terminal or CI, and read a failure.
- Replay videos: What the video shows, how to pace it and where to watch it.
- Environments, variables and secrets: Where a test runs, how its state is reset and how it gets its logins.
- Existing Playwright suites: Track the Playwright tests you already have.
Beyond tests
- Code reached: Which functions a real browser actually ran.
- Visual checks: A free audit of the rendered page, and a verdict on a screenshot.
Connect
- CI coverage: Have GitHub Actions upload coverage on every push.
- Agent skill and instructions: Teach your agent the loop so it runs without being asked.
- Linear: Link branches to their Linear issues.
Reference
- CLI commands: Every verifaied command and its main options.
- MCP tools: Every tool your agent can call.
- Repository settings: Every setting on a repository's Settings page.
- Plans and limits: What each plan includes and which features are paid.
- Troubleshooting: The common problems and their fixes.