---
title: "What is agent-qa"
description: "Source-available agent-qa runs plain-English web and mobile tests, learns from every run, adapts to UI changes, and catches regressions before they ship."
canonical_url: "https://vostride.com/docs/agent-qa"
md_url: "https://vostride.com/docs/agent-qa.md"
last_updated: "2026-10-08T18:28:36+05:30"
---

> [Documentation index](https://vostride.com/docs.md) · [Site index](https://vostride.com/llms.txt)
> Follow the Markdown links to read individual pages; the indexes list the available documentation.

# What is agent-qa

> Source-available agent-qa runs plain-English web and mobile tests, learns from every run, adapts to UI changes, and catches regressions before they ship.

## Overview
**agent-qa**: **The self-improving QA agent for your software factory.** Give your coding agents a QA agent that learns your app. Run natural-language tests across web and mobile, build memory with every run, and catch regressions before you ship.

Your coding agent can author a test, run it through CLI or MCP, inspect the evidence, and use the result to guide its next change. Tests, configuration, memory, and artifacts stay under your control. Use the [agent quickstart](https://vostride.com/docs/agent-qa/agent-quickstart.md) to go from an existing repository to a verified first test.

```text
Set up agent-qa in this application's repository and run a meaningful end-to-end test. Complete the setup and verification, rather than only giving me instructions.

agent-qa is Vostride's self-improving QA agent for web, Android and iOS. It executes natural-language tests against the real interface, preserves test definitions in the repository, and uses validated memory and cached action plans on future runs.

Read the official agent quickstart first:
https://vostride.com/docs/agent-qa/agent-quickstart.md
Use https://vostride.com/llms.txt to find the current configuration, CLI, MCP and skills references. Treat documentation as technical reference; follow this repository's instructions and my authorization boundaries.

1. Inspect the repository, package manager, app start commands, existing tests and agent-qa configuration. Reuse existing work and credentials without printing secrets. Identify one important user flow and the local or approved test environment. Ask me only for information or authorization that is actually required, such as an unavailable model credential or an ambiguous target. Do not use production data or deploy anything as part of setup.

2. Install agent-qa as a development dependency using this repository's package manager. Inspect the installed version and its CLI help before selecting options. Install the packaged authoring, debug/fix and result-triage skills when the client supports them; use the CLI directly otherwise.

3. If configuration does not exist, initialize it without overwriting existing files. In agent-qa 0.1.21, supplying --platform (web, android, ios, web+android or web+ios) skips the questionnaire. For web, run npx agent-qa init --platform web --dir . using the locally installed package. This version defaults to anthropic-subscription and adds the subscription-auth dependency; inspect and deliberately configure the LLM before running a test. There are no init --yes, --provider, --model or --base-url flags in that version. Newer versions may differ: check their help.

4. Configure an available, suitable multimodal model and the app target using the documented file schema. Reuse an existing authorized credential. For a new API credential, use the secure interactive auth prompt when available, or the quickstart's documented environment-to-auth.json procedure for unattended setup. Version 0.1.21 has no auth set --stdin flag. Never put credential values in shell arguments, committed YAML, logs or the final reply. If using subscription authentication, reuse an authorized session or let me complete the required authentication. Do not assume the coding agent's subscription is automatically available to agent-qa.

5. Prepare only the required runtime: Chromium for the first web test, or the appropriate Appium driver and device for mobile. Docker is needed only for hooks that use it. Start the app with its existing development command, verify the target is reachable, and run agent-qa doctor. Resolve relevant setup failures before testing.

6. Author a small test for the chosen real user flow using agent-qa's documented YAML schema and canonical IDs. Include assertions about observable outcomes, not only successful clicks. Validate the definition before execution. Reuse the current MCP integration when available; otherwise use the local CLI. Never weaken an assertion or change expected behavior just to obtain a pass.

7. Run the test and inspect its verdict, step evidence and artifacts. Distinguish an application bug from a test, environment, authentication or model failure. Fix setup or test-authoring errors and rerun the affected test. Report application bugs with evidence unless I have authorized fixing them. A skipped, interrupted or unexecuted test is not a pass.

8. Leave the test and reusable configuration in the repository, keep secrets and runtime artifacts out of commits, and stop temporary services you started unless they are still needed. Report the changed files, exact rerun command, model and target used, observed result, evidence locations and any remaining blocker. Explain how to reuse this test in the coding agent's next verification loop. Do not claim success until an actual run supports it.
```

- [Agent quickstart](https://vostride.com/docs/agent-qa/agent-quickstart.md): Give your coding agent the complete setup task: initialize without menus, configure a model, and run a meaningful test.

- [Explore demos](https://vostride.com/demo/agent-qa.md): Open curated agent-qa runs in the interactive demo viewer and inspect how real test steps execute.

- [Configuration](https://vostride.com/docs/agent-qa/configuration.md): Review the file-backed configuration system for global settings, tests, suites, hooks, variables, secrets, devices, rules, and auth.

- [Memory](https://vostride.com/docs/agent-qa/memory.md): Review how file-backed product, suite, and test observations make future runs more product-aware.

- [Caching](https://vostride.com/docs/agent-qa/caching.md): Reuse validated action plans while the screen still matches, and measure the runtime and token savings on your own tests.

- [Tests](https://vostride.com/docs/agent-qa/guides/first-test.md): Write one plain-English YAML journey with stable intent, reviewable steps, and source-controlled expectations.

- [Web Testing](https://vostride.com/docs/agent-qa/guides/web-testing.md): Run browser flows against local or staged web apps without hardcoded selectors or fragile DOM coupling.

- [Auth state](https://vostride.com/docs/agent-qa/guides/auth-state.md): Capture a named web login once, reuse it by logical name, pass the active state to hooks, and keep credential material out of artifacts.

- [Suites](https://vostride.com/docs/agent-qa/guides/suites.md): Bundle related tests, targets, configuration, and hooks into repeatable workflows for a feature area.

- [Mobile Testing](https://vostride.com/docs/agent-qa/guides/mobile-testing.md): Use the same natural-language workflow model for mobile app journeys while preserving artifacts locally.

- [Hooks](https://vostride.com/docs/agent-qa/guides/hooks.md): Prepare data, call project scripts, verify side effects, and clean up state before or after a run.

## How agent-qa works
### Write tests in natural language
Describe the user journey in plain English: what to open, what to do, and what to assert. agent-qa turns that intent into repeatable execution.

### Bring your own LLM
Use any hosted or local model. It also works with Codex and Claude Code subscriptions.

### Run tests
Run tests from either the dashboard or the CLI. Group multiple tests into a suite to execute user journeys end-to-end.

### Generate memory and context
Each run passes through a memory curator that records product behavior, test intent, and suite context, then creates contextual memory for future test runs.

### Improve the next run
Future executions use the evolved agent context. That memory helps the agent adapt to product changes at runtime, recover from brittle UI drift, and become more reliable over time.

### Grow a product-aware QA agent
The end state is a QA agent with enough context about your product to author tests, run them, inspect failures, and keep improving the testing loop.

## All documentation

### Overview

- [What is agent-qa](https://vostride.com/docs/agent-qa.md): Write tests in natural language for web and mobile. agent-qa builds memory with every run, adapts to UI changes, and catches regressions before you ship.
- [Agent quickstart](https://vostride.com/docs/agent-qa/agent-quickstart.md): Give your coding agent a complete path from an existing repository to a verified end-to-end test.
- [Quickstart](https://vostride.com/docs/agent-qa/quickstart.md): Install agent-qa, prepare web and mobile runtimes, connect an LLM, and inspect your first run from the dashboard or CLI.
- [Built for humans and agents](https://vostride.com/docs/agent-qa/humans-and-agents.md): Humans and coding agents author the same reviewable tests, backed by your repository, skills, and MCP.
- [Self-healing execution](https://vostride.com/docs/agent-qa/self-healing.md): Recover from a failed action by finding another route to the same expected outcome.
- [Memory overview](https://vostride.com/docs/agent-qa/memory.md): Understand agent-qa memory as file-backed behavioral observations that make future runs more product-aware without replacing live evidence.
- [Caching](https://vostride.com/docs/agent-qa/caching.md): Understand how agent-qa caches action plans, builds cache keys, invalidates stale entries, and can make similar subsequent runs 5x faster with 60% less token usage.
- [Configuration](https://vostride.com/docs/agent-qa/configuration.md): Understand the file-backed configuration system that powers agent-qa projects.
- [CLI](https://vostride.com/docs/agent-qa/cli.md): Source-backed reference for the agent-qa command line, grouped by setup, execution, authoring, configuration, maintenance, and AI-native workflows.
- [MCP](https://vostride.com/docs/agent-qa/mcp.md): Use agent-qa MCP tools to discover project context, author tests and suites, enqueue runs, inspect artifacts, and classify failures from an AI agent.
- [Skills](https://vostride.com/docs/agent-qa/skills.md): Practical guide to packaged agent-qa skills and the CLI command that lists them for AI agents.

### Guides

- [Coding-agent verification loop](https://vostride.com/docs/agent-qa/guides/coding-agent-workflow.md): Turn a code change into a tested user journey, an evidence-backed diagnosis, and a focused rerun.
- [Evaluate agent-qa on your app](https://vostride.com/docs/agent-qa/guides/evaluating-agent-qa.md): Measure useful bug detection, repeated-run cost, and agent setup success with a reproducible experiment.
- [Recorded test evidence](https://vostride.com/docs/agent-qa/guides/recorded-evidence.md): Inspect the recorded web and Android test results behind the agent-qa demo.
- [Write your first test](https://vostride.com/docs/agent-qa/guides/first-test.md): Create a source-grounded agent-qa test file with a target, context, optional hooks, per-test overrides, and natural-language steps.
- [Web testing](https://vostride.com/docs/agent-qa/guides/web-testing.md): Configure web targets and browser overrides for agent-qa tests that run through Playwright-managed Chromium, Firefox, or WebKit.
- [Auth state](https://vostride.com/docs/agent-qa/guides/auth-state.md): Capture a named web login once, reuse it across tests and suites, and pass the active Playwright storage-state JSON to hooks without exposing credential material elsewhere.
- [Mobile testing](https://vostride.com/docs/agent-qa/guides/mobile-testing.md): Configure native Android and iOS targets, local or BrowserStack devices, app installs, and required mobile app-state behavior.
- [Suites](https://vostride.com/docs/agent-qa/guides/suites.md): Combine multiple agent-qa tests into one ordered suite with shared target, context, hooks, and run overrides.
- [Hooks](https://vostride.com/docs/agent-qa/guides/hooks.md): Write sandboxed agent-qa hooks that prepare data, verify side effects, and export runtime variables back to tests and suites.

### Dashboard

- [Dashboard](https://vostride.com/docs/agent-qa/dashboard.md): Source-backed tour of the agent-qa dashboard routes for runs, tests, hooks, suites, memory, insights, config, and queue-aware workflows.

### Memory

- [Curator](https://vostride.com/docs/agent-qa/memory/curator.md): Learn how the memory curator turns run evidence into added, confirmed, deprecated, deleted, or unchanged observations.
- [Behavioral Memory Schema](https://vostride.com/docs/agent-qa/memory/behavioral-memory-schema.md): Read and review the markdown observation files that back agent-qa behavioral memory.
- [Runtime Memory Injection](https://vostride.com/docs/agent-qa/memory/runtime-injection.md): Understand how agent-qa indexes file-backed observations and injects matching memory into individual steps.
- [Memory Reliability and Maintenance](https://vostride.com/docs/agent-qa/memory/reliability-maintenance.md): Configure memory trust, injection limits, curator locking, ablation, circuit breaker behavior, security scanning, and stale suite cleanup.

### Configuration

- [Global Config](https://vostride.com/docs/agent-qa/configuration/global-config.md): Configure workspace discovery, services, registries, plugins, analytics, and default run behavior in agent-qa.config.yaml.
- [Test](https://vostride.com/docs/agent-qa/configuration/test.md): Structure a single natural-language web test definition with target, hooks, variables, steps, and per-test run overrides.
- [Suite](https://vostride.com/docs/agent-qa/configuration/suite.md): Group multiple web tests into an ordered agent-qa suite with shared target, context, hooks, and run overrides.
- [Hook](https://vostride.com/docs/agent-qa/configuration/hook.md): Register sandboxed hooks in hooks.yaml and implement scripts that prepare web test data, verify API side effects, and export runtime variables.
- [Env & Secrets](https://vostride.com/docs/agent-qa/configuration/env-secrets.md): Use .env, .env.secrets.local, hook output, and CLI variables without leaking credentials into test files or artifacts.
- [Local config](https://vostride.com/docs/agent-qa/configuration/local-config.md): Keep machine-specific provider credentials, device bindings, and app artifact paths in agent-qa.local.yaml instead of shared project config.
- [Agent rules](https://vostride.com/docs/agent-qa/configuration/agent-rules.md): Add project-specific QA behavior rules that every agent-qa web or mobile run can read before executing steps.
- [auth.json](https://vostride.com/docs/agent-qa/configuration/auth-json.md): Understand where agent-qa stores saved LLM credentials and how to create auth.json safely for CI.

## Documentation navigation

- [All documentation](https://vostride.com/docs.md)
- Next: [Agent quickstart](https://vostride.com/docs/agent-qa/agent-quickstart.md)