​

Introduction

Qodex is an agentic, autonomous QA platform you talk to. It is built for engineering teams shipping an API and a web app every day, where QA is the bottleneck. Instead of writing and maintaining every test by hand, you describe what to test in plain English, and an agent does the rest: it explores your real app, writes the tests, and keeps running them. In plain-English chat, Qodex tests APIs and web apps, reviews code changes, and probes security. It explores the target with a real Chrome browser or direct API calls, learns how it behaves, creates runnable Playwright or HTTP scenarios, and saves them for repeatable runs. When a test fails, it triages the evidence as a real bug, stale test, or environment problem.

​

How Qodex works at a high level

Qodex turns a testing brief into reusable test coverage.

• Scenarios describe what should be tested, including steps, assertions, tags, and lifecycle state.
• Scripts are generated standard Playwright or HTTP code that can run against your environments.
• Findings are bugs, failures, or vulnerabilities discovered during a run, with severity, reproduction steps, and evidence.

​

What you can test

​

How tests run

Qodex runs the same saved scenarios in three modes.

​

Why replays are cheaper

Most AI QA tools charge per run because every replay is an LLM call. Costs scale with suite size, even when the app has not changed. Qodex uses AI when a test is created or repaired, not every time it runs. The generated script is standard Playwright or HTTP code, parameterized by environment variables, and replayed without calling an AI model. Your nightly regression runs consume execution resources, not AI usage. UI scenarios use natural-language steps resolved against the live page. A successful first run creates an AI-free replay cache; if a page changes enough for the cached path to fail, Qodex re-resolves the step and repairs the test.

​

Where to go next

​

Common questions

Who is Qodex for? Engineering teams that ship an API and a web app frequently and cannot keep manual QA in step with the pace. If your test coverage lives behind the product instead of alongside it, Qodex is built for you. How is Qodex different from writing tests by hand? With hand-written tests, an engineer authors each scenario, maintains the selectors and assertions as the app changes, and pays that maintenance cost forever. With Qodex, an agent authors the tests from a plain-English brief, self-heals the UI ones when a page changes, and keeps proposing coverage for new endpoints and pages. You still get standard Playwright and HTTP code you can read and check in. Do I need to write code or test scripts to start? No. You describe what you want tested in chat. Qodex explores the app and writes the runnable scripts for you. You can read, edit, and commit those scripts, but you do not have to write them to begin. What is agentic QA, or autonomous testing? It means an AI agent, not a person, drives the testing loop: it explores the app, decides what to test, authors the scenarios, runs them, and triages the failures. Qodex is agentic because a coordinator agent and specialized sub-agents do that work, and autonomous because the saved suite keeps running on every pull request and deploy without someone kicking off each run.

​

LLM-readable docs

Every page is also published as .md for LLM ingestion. See llms.txt.