Kane CLI vs Factory: Who Checks a Droid's Work?
Droids verify their own pull requests. Kane CLI gives an independent pass or fail with evidence, from a tool that did not write the code.
or read the documentation
Why teams pair Kane CLI with Factory Droids
Factory is built for enterprise delivery. Droids run from the terminal, the Factory App, Slack, Jira, Linear and CI, keep working on persistent Droid Computers, and deliver a change end to end, with SSO, audit logging and on-premise options your security team will sign off on.
The catch is who grades the work. A Droid checks its own work with /verify in the run that wrote it, against the claim it was asked to confirm, and the next run re-verifies whatever the Droid decides to check.
Kane CLI adds the independent check. You give it the journey the change touches, it drives a real browser, asserts the result and hands back a verdict with evidence, in the Droid's run and in your CI.
Want the numbers? The Kane CLI benchmark write-up shows how Kane CLI scores as a testing agent, and the agentic software factory post covers what enterprises need around coding agents.
Kane CLI vs Factory Droids
One agent ships the change, the other proves it works.
| Capability | Kane CLI (TestMu AI) | Factory Droids |
|---|---|---|
| What it is | A testing agent that verifies a flow | An enterprise coding-agent platform that ships the change |
| Who writes the test | You or your agent, as a natural language objective | A Droid, from a prompt or a /qa-test flow |
| Who grades the result | Kane CLI, separate from the agent that wrote the code | The same Droid, with /verify in the run that wrote it |
| Verdict | Verified pass or fail with built-in assertions | CONFIRMED, REFUTED or INCONCLUSIVE |
| Evidence | Screenshots, logs, step trace, shareable links, dashboard | Captured evidence, /demo video, session transcript |
| Tests outlive the run | Yes. The objective lives in your repo and CI | Saved, scheduled browser suite not documented |
| Mobile apps | Native apps on Android Emulator and iOS Simulator | iOS device emulation in a Chromium browser |
| CI gate | Exit codes 0 to 3 in any runner | droid exec runs in CI |
| Agent-native output | --agent emits structured NDJSON | A Droid is the agent and can call Kane CLI |
| Code export | One command to export Playwright code | Browser checks are not exported |
| Starting price | Free: 10,000 credits for 30 days | Pro $20 a month; no free plan listed |
What you get with Kane CLI
The checks a Droid grades itself, verified by a separate tool.
A second opinion on every Droid
A Droid verifies what it wrote. Kane CLI checks the same journey from outside the run, so the agent that wrote the code is not the only one grading it.
Natural language objectives
Describe the journey in one line. Kane CLI plans the steps, drives Chrome, and resolves elements by intent, so there are no selectors for the Droid or you to maintain.
Self-heals when the UI changes
A renamed class or moved button does not fail the check. Kane CLI adapts to the changed UI and pushes through up to 50 steps until the journey is verified.
Agent-native output
The --agent flag emits structured NDJSON with a failure screenshot, so a Droid can read the result, fix the failure, and run the check again before it opens the pull request.
Checks that stay in your repo
Keep the objective in your repo. The next change, the next build and the next agent run the same check, and every run lands in Test Manager.
Web and native mobile
Run the same objective against the desktop browser, or against a native app on an Android Emulator or iOS Simulator on macOS Apple Silicon.
Build up confidence locally
Start in your terminal
Validate on the cloud
Release with confidence
Built for agents and humans, on one engine
Kane CLI runs the same engine from your terminal, your CI and your coding agent.
Droids build, Kane CLI verifies
Let Droids deliver the change end to end. Point Kane CLI at the journeys that change touches and know whether it works before you merge.
Same check in the run and in CI
A Droid runs Kane CLI with --agent in its session; droid exec or your pipeline runs the same objective headless and gates on the exit code.
One verified contract for the team
Whether a Droid, another agent or an engineer runs it, every run lands in the same dashboard, so reviewers read one source of truth.
Test what a Droid ships in three steps
Install
Run npm install -g @testmuai/kane-cli and sign in with your TestMu AI account, or point a Droid at the Kane CLI agent guide and let it install and authenticate on its own.
Describe the journey
Write the flow the change touches as one sentence. The Droid runs it with --agent, or you run it from the terminal.
Gate the pull request
Add the same objective to CI with --headless. A pass is exit code 0; anything else blocks the merge and points to the step that failed.
Get the technical rundown
Documentation
Everything you need to install, configure, and run Kane CLI in under 2 minutes.
Frequently asked questions
Factory is an enterprise coding-agent platform: Droids deliver a software change end to end from the terminal, the Factory App, Slack, Jira, Linear or CI. Kane CLI is a testing agent. It does not write your product code; it takes a natural language objective, drives a real Chrome browser, and reports whether the journey worked, with screenshots and logs. A Droid builds the change, Kane CLI checks it.
They do. A Droid runs /verify in the run that wrote the code and returns CONFIRMED, REFUTED or INCONCLUSIVE with captured evidence, and /demo records a video. That verdict comes from the same agent that wrote the code, against the claim it was asked to confirm. Kane CLI adds a second opinion: a verified pass or fail from a separate tool, with an exit code your CI can gate on.
Yes. Point the Droid at the published Kane CLI guide and it installs, authenticates, and runs each flow with the --agent flag, reads the structured NDJSON result, and fixes a failure before it opens the pull request. The same objective can run from droid exec in CI or on a schedule through Automations.
Yes. A Kane CLI objective is a line of text you keep in your repository or pipeline, so the same check runs on the next change, the next build and the next agent. Every run syncs to Test Manager. A saved, scheduled browser regression suite is not part of Factory's docs.
Yes. The default target is the desktop browser, and on macOS Apple Silicon you can point the same natural language objective at a native app on an Android Emulator or iOS Simulator. Factory's agent-browser offers iOS device emulation in a Chromium browser; native mobile app testing is not documented.
Kane CLI is free to install, and new accounts get 10,000 free credits, valid for 30 days. Factory publishes its own plans: Pro at $20 a month, Plus at $100, Max at $200, Teams at $60 a month plus $40 per seat, and custom Business and Enterprise pricing. No free Factory plan is listed.
Teach your agent the right skills
Point a Droid or any AI coding agent at the Kane CLI guide and it will install, authenticate, and run verified browser flows on its own.
Point your agent to: testmuai.com/kane-cli-agent/AGENTS.md