​

Introduction

Qodex is an AI QA platform for APIs, web apps, pull requests, and security workflows. Instead of writing every test by hand, you describe what you want tested. Qodex explores the target with a real Chromium browser or direct API calls, learns how it behaves, creates runnable Playwright or HTTP scenarios, and saves them for repeatable runs.

​

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 the generated Playwright or HTTP code that can run against your environments.
• Findings are bugs, failures, or vulnerabilities discovered during a run, with severity 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 the LLM when a test is created or repaired, not every time the test runs. The generated script is standard Playwright or HTTP code, parameterized by environment variables, and replayed deterministically. Nightly regression runs at Playwright or HTTP cost, not OpenAI cost. UI scenarios use an intent runner today with a step cache, so a successful first run feeds zero-LLM reruns. A fully deterministic UI runner is on the roadmap.

​

Where to go next

​

LLM-readable docs

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