The web automation agent that proves the work

Any multi-step flow a person could do in a browser: logins, sign-ups, search and filter, cart and checkout, form submissions, dashboard checks, and reading a value back off the page. The web automation agent chains these into one objective and pushes through cookie banners, modals, and redirects up to 50 steps per flow. Because it anchors to the user-facing element rather than a selector, a reworded label or a new CSS class does not stall the workflow partway through.

The honest position from TestMu AI: the LLM is not deterministic, but the validation contract is. The model decides how to reach an element, and that path can vary run to run, but it does not get to decide the task passed. A pass is granted only when the expected state is verified through explicit evidence: DOM state, stable selectors, accessibility labels, URL changes, network responses, screenshots, console logs, or your own assertions. In CI you key the pipeline off the evidence-backed exit code: 0 when the state is verified, 1 on a failed assertion, 2 on an error such as auth, and 3 on timeout.

Yes. Because the verdict is machine-readable, AI coding agents can drive the web automation agent and close their own loop. Run Kane CLI with the --agent flag and it streams NDJSON, one typed event per line, ending in a run_end event carrying the verdict, an evidence summary, extracted values, and a dashboard link. Claude Code, Cursor, Codex, and Gemini CLI parse that stream to learn whether the flow they built actually works. Point your agent at the guide at testmuai.com/kane-cli/agents.md and it installs, authenticates, and runs the workflow on its own.

When one browser on your laptop is not enough, the same objective runs on Browser Cloud, the browser infrastructure built for AI agents. It provisions real, full-featured Chrome sessions on demand and runs many in parallel, with a built-in tunnel to reach localhost and staging, automatic session video and logs, and persistent login state across runs, all on the cloud that powers 1.5 billion tests a year for 18,000+ enterprises. Start in your terminal, then scale out without a rewrite.

Yes. A web automation agent is not only for verification. Kane CLI can read a value off the rendered page and return it in the run_end event, so you can pull a price, a status, or a confirmation number as structured output. For higher-volume data and extraction workloads, see AI web scraping and the Firecrawl alternative, which run on the same Browser Cloud infrastructure.

Yes, Kane CLI is free to install and free to run against your own browser, so you can prove out the LLM-perception-plus-evidence workflow at zero cost. The Starter tier adds 100 credits with no credit card. Cloud runs on the TestMu AI grid are billed against your plan only when you scale to remote browsers, geo coverage, or parallel sessions. Start free and run a real web workflow with shareable evidence in under five minutes.