Verification · Testing · End-to-end browser tests
Agent-driven exploration
An LLM agent drives the browser from a natural-language description of the flow.
How to build it
- Write each flow as a short natural-language goal with the expected end state.
- Run the agent against a test account and seeded data, never production data.
- Keep the agent's steps and the final page state as the result of each run.
Signals in a repository
- Flow description files, such as markdown or YAML goals, in an e2e or agent directory.
- Agent run logs or recorded step transcripts attached to CI results.
In practice
No scanned repository runs a tool for this check. The steps above are the only guidance.