Skip to main content
Writing the change is only part of finishing it. Validation is the work an agent does afterward to show that the result builds, passes the right tests, and behaves as expected. FlowDeck always requires project tests and repository checks. The Validation settings control the extra runtime checks and evidence an agent gathers after those required checks, so you can choose between a faster handoff and a more comprehensive review.

​
Why FlowDeck validates more

FlowDeck is built to let agents do more than edit files. An agent can use the project’s saved target to build and test, run the real app, exercise changed flows, inspect logs, and capture evidence from simulators and devices. That makes it possible to catch problems a code diff or clean build cannot reveal, such as clipped text, a broken interaction, or state that fails only after the app is launched. Balanced is the default because it closes that loop without collecting evidence that does not help explain the result. UI work will usually be run and shown when a screenshot materially proves the change; a non-visual change may need only tests and a concise report.

​
Choose a starting point

The preset at the top of Settings ▸ AI Workflows ▸ Validation sets every option below it. You can then change any option independently. When you do, the preset reads Custom. Choosing a named preset again resets all five options to that preset.

Lean

Relies on required tests and project checks. The agent runs the app only when those checks cannot prove the behavior, stays on the saved target, skips screenshots and recordings, and reports the result briefly.

Balanced

Runs changed features on the saved target, adds another target only for a meaningful risk, captures visual evidence when it helps, and gives a clear summary. This is the default.

Thorough

Exercises changed and adjacent flows, edge cases, and repeat interactions across multiple targets. It captures every relevant visual state and motion, then produces a detailed matrix.

​
Customize each method

​
Run the app

Controls how much runtime behavior the agent exercises after the required checks pass.

​
Screenshots

Controls still-image evidence. It does not decide whether the agent runs tests or checks the app.

​
Screen recordings

Controls video evidence for behavior that a still image cannot explain well.

​
Additional devices

Controls whether the agent repeats relevant runtime checks beyond the saved target.

​
Final report

Controls how much validation detail appears in the agent’s final response. It changes the report, not the checks that are required.

​
What never changes

Validation preferences never let an agent skip required tests, repository gates, safety rules, permission requirements, or honest reporting. An agent must not claim a check or artifact it did not produce. A setting can reduce extra runtime work or evidence, but it cannot turn a failed check into completed work. Changes take effect when a session is next configured or restored, and for Team workers hired after the change. They do not rewrite the instructions of an agent that is already running.