Agents & Prompts

The agent's standing instructions, four prompt files every Project carries, what each does, and which ones you edit.

The prompts/ folder is what you'd tell a new tester on day one, standing instructions the agent gets before every run. Every new Project is seeded with four files; edit them on the Agents page or in any editor.

File	Holds	You edit it?
`system_capabilities.md`	The agent's identity and error discipline	Rarely, the defaults keep runs honest
`device_information.md`	Quirks of the machine under test	Only when the machine has quirks
`ui_information.md`	How your application works	Yes, the file you invest the most in
`report_format.md`	Structure and statuses of the report	When your reporting needs differ

System capabilities

system_capabilities.md defines what the agent is and how it behaves when things go wrong. The defaults are deliberately strict:

You have a maximum of 2 attempts per step. If a step does not succeed after 2 attempts, stop immediately. Do not try a third time.

Two conventions the agent relies on:

Credentials never live in a test. A step references a named secret; the agent types a placeholder and the real value is substituted at execution time, hidden from the model.
Scratchpad: the agent can persist notes across phases with the scratchpad tools, but only when a test explicitly instructs it to.

Device information

device_information.md, machine quirks the agent can't see for itself, keep it small. The agent already sees the screen, so OS and display basics rarely need describing:

* Always execute on display 1.
* The corporate lock screen appears after 5 minutes of inactivity.

Swap this file when retargeting a Project at a different machine.

UI information

ui_information.md, where the agent learns your application, the domain knowledge that lets a colleague without domain knowledge execute your tests. The default ships as placeholders:

## Navigation
The application has these primary areas: Dashboard, Records, Settings…

## State indicators
"Login state is shown top-right: a green dot means signed in, red means the
session expired — sign in again."

## Dialogs & quirks
"Destructive actions open a centered confirmation dialog that must be
confirmed or dismissed before continuing."

This is also where you steer how the agent operates your UI, "enter numbers via the on-screen numpad, never the keyboard" (more).

Report format

report_format.md, the template for every report the agent writes: title, Test Case ID, date, status, and the per-step sections. Two parts are load-bearing:

The **Status:** line is parsed by the runner to set the run's result, remove it and a passing test is recorded as BROKEN.
The status definitions (PASSED / FAILED / SKIPPED / WARN / BROKEN) are the status vocabulary your reports and Dashboard use.

Customize the sections when your organization needs different evidence, keep the **Status:** line.

Per-suite instructions

Standing instructions that apply to one suite only, not to the whole Project, go into the suite's rules.md, which accumulates with these prompt files at run time.