Animations are illustrative. Real traces and benchmarks are in the repo.
Explore the app.
Describe the action.
Your agent sends targets and claims through MCP. Jev picks from structured candidates and judges accessible state.
Passed actions.
Written in plain language.
The flow takes shape as you explore. Only passed actions become steps in the saved spec.
The session ends.
The test stays.
Save writes the passed steps as YAML. Read it. Edit it. Commit it.
Run it again.
Without the agent.
The CLI replays your saved flow from its lock file. In no-judge mode, that takes no model call and no API key.
● ● ●demo.playwright.dev / todomvc
A little less to do.
Your test environment.
What needs to be done?
buy milk
write a regression test
“Add buy milk to the list.”
expecta todo item named ‘buy milk’ is listed
add-todo.yamlSaved spec
name: add a todo
url: https://demo.playwright.dev/todomvc
steps:
- goto: /
- fill:
target: "the new todo input"
value: "buy milk"
- press: Enter
- expect: "a todo item named 'buy milk' is listed"
Your terminal
$ npx -p @gabe4coding/plain plain --mode no-judge add-todo.yaml
✓ goto
✓ fill
✓ press
✓ expect
Flow replayed
No coding agent. No model call.
A changed step is inconclusive, never passed.
Before you run it.
Does replay still cost model calls?
Not in no-judge mode. It replays the committed lock file with no Jev call and no API key. A step that changed is inconclusive, never passed. The default auto-healing mode replays the lock file too, but Jev repairs changed steps and judges every claim. Run modes ↗ · Measured costs ↗.
What is the lock file?
A passing run writes a lock file next to each spec: a locator for each target and a hash of each passing claim. Commit it with the spec. A diff shows which step changed. It holds no values from env or hooks. Lock files ↗.
What happens when a target is ambiguous?
A weak pick is inconclusive, not passed. Write specific targets and scope claims with within. Thresholds and phrasing ↗.
Can it understand layout and visual appearance?
Jev reads structured candidates and accessible state, not screenshots. Spatial prompts also receive rendered bounds. Bounds do not prove color or image appearance. Evidence and limits ↗.
What do I need, and where is my key?
Node 22+, npm and a TypeSafe or Vercel AI Gateway key. All CLIs read ~/.config/plain/.env. Desktop needs accessibility permissions. Mobile needs Appium and a configured device. Requirements and key options ↗.
Is this a replacement for every test?
No. Keep explicit conventional tests for exact assertions and pixel-level checks. Use test environments only. Stop before payment, booking or sending. Usage rules ↗.