# Frazer QA and Frazer Browsers

> Frazer QA tests every change on a live preview, and Frazer Browsers gives agents browsers and desktops. A preview is a live environment for one change at one URL on frazer.run, sharing a baseline and copying only what changed. Frazer answers what a change affects and what to test at three depths, runs the tests with no model where it can, records results as evidence that Frazer Reviewer and auto-merge read, and gives agents a browser that sees pages as compact text with refs and records every step.

Part of Frazer's docs for agents. Every page on frazer.ai: https://frazer.ai/llms.txt. Every docs page: https://frazer.ai/docs/llms.txt.

## How agents should use Frazer QA and Frazer Browsers

- Test where the change runs: `fir pr preview`, `fir pr affected`, `fir pr test`. A test passes on checked backend state, and a `no_verdict` is never a pass.
- Sign in to a preview as a persona with a login handle; never ask for or type a real password, never solve a challenge and never pay.
- Browse your organization's own apps; an outside origin works only when the project's browser policy allows it, signed as an agent, and you may propose an origin, never approve one. Production payloads, probes and snapshots need a capture approval a person gives per service.

## Pages

- [Templates and previews](https://frazer.ai/docs/previews.md?from=llms-txt): Create a new service from a template in one plan, and get a preview environment for every pull request with only the apps it changes and its own copy of staging data.
- [Frazer QA](https://frazer.ai/docs/previews/tests.md?from=llms-txt): Frazer QA tests every change on a live preview: a preview for every workspace, pull request, stack, plan level, test batch, program, release candidate or past moment, at one URL on frazer.run, sharing a baseline and copying only what changed; what a change affects across repositories; test plans at three depths (smoke, full, pre-release); test runs that replay with no model, check backend state, load, test the tests and emulate faults; results that Frazer Reviewer and auto-merge read as evidence.
- [Frazer Browsers](https://frazer.ai/docs/agents/browsers.md?from=llms-txt): Frazer Browsers: browsers and desktops for agents. A browser any agent drives, next to a preview, in its own cell or on a devbox: compact snapshots with stable refs, scripts of many steps in one call, a receipt for every step, logins as personas with no real credential, a flight recorder of every run, flows that rerun with no model, reproductions of issues that Frazer CI confirms, and desktops for apps outside the browser.

## Optional

- [Full text of these pages](https://frazer.ai/docs/previews/llms-full.txt): 3 pages, 67,895 characters, about 16,974 tokens