# Blue Codens

> Updated: 2026-07-12
> Blue Codens is an AI QA automation tool that auto-generates and runs E2E tests (Playwright) from specs and natural language, and uses AI to analyze failures down to their root cause and auto-draft bug reports. It's part of the Codens Suite.

## What is Blue Codens

Blue Codens is an AI-powered QA platform: it turns specs, PRDs, code, or natural-language requirements into structured test cases, drives an autonomous browser agent (Claude Agent SDK + Playwright MCP) to extract Playwright E2E test code from the live app, runs those tests headless on Scale-to-Zero infrastructure, and — when a test fails — has AI analyze the failure and draft a bug report. It is built for QA teams (and teams without a dedicated QA specialist) who need E2E coverage without hand-writing and hand-maintaining every test.

Differentiator: most QA tooling stops at detecting or triaging a failure. Blue Codens hands detected bugs to Red Codens, which auto-generates a fix PR, and Blue Codens re-runs the tests against that fix — closing the loop from detection to fix to re-verification without a human in the middle.

## Key facts

- Pricing: 5-tier credit-based subscriptions — Free (14-day trial, 100,000 credits, no card) / Hobby ¥3,000 (300,000 credits/mo, 5 seats) / Pro ¥10,000 (1,000,000 credits/mo, 10 seats) / Business ¥50,000 (5,000,000 credits/mo, 25 seats) / Enterprise (custom, unlimited credits). Credits are shared across the whole Codens family (Red / Blue / Green / Purple). Playwright execution itself does not consume credits.
- Dogfooding stat (Codens-wide): 65% of merged PRs are AI-generated (www.codens.ai/stats, measured via the GitHub API).
- Case study (Codens-wide): 3 business staff + 1 engineer at PORTAMENT Inc. shipped 5 projects / 1,000+ PRs in 1.5 months using the Codens suite.
- Case study (Codens-wide): Widsley Inc. shipped a high-difficulty telephony-control project in 3 months with 1 PM/implementation engineer + 2 QA staff.
- Stack: Claude API for structured test-case generation, Claude Agent SDK + Playwright MCP for exploratory E2E, ECS Fargate (Scale-to-Zero) Playwright Workers, Server-Sent Events for live progress.

## How it works

1. Ingest test sources — a spec, PRD, code, natural-language requirements, or a target URL. PRDs can be pulled directly from Green Codens.
2. AI test case generation — the Claude API produces structured test cases (steps, expected results, priority, type: manual / automated / E2E) in one batch.
3. Exploratory E2E generation — Claude Agent SDK + Playwright MCP autonomously drives the app, discovers real screen flows and selectors, and extracts Playwright test code.
4. Run with Playwright — tests execute headless on a dedicated ECS Fargate Playwright Worker (Scale-to-Zero); progress, screenshots, and logs stream over SSE.
5. AI bug analysis & reporting — on failure, AI produces a bug report with reproduction steps, root-cause hypotheses, and links to similar bugs.
6. Red Codens hand-off — the bug is forwarded to Red Codens, which auto-generates a fix PR; Blue Codens re-runs the tests until the suite goes green. Fully unattended.

## Comparison

(Comparison reflects each vendor's publicly available information as of July 2026 — a general overview, not a claim of definitive superiority.)

- vs. Manual QA: Manual QA offers human judgment and flexible exploratory testing but doesn't scale with headcount. Blue Codens auto-generates and continuously maintains the test suite from specs and the live app.
- vs. Running Playwright on your own: full control and no vendor lock-in, but every test is hand-written and hand-maintained by engineers. Blue Codens generates and grows the Playwright suite automatically and still leaves you with portable Playwright code.
- vs. Autify (Nexus/Genesis): strong no-code test authoring and "Fix with AI" locator auto-healing, and Genesis converts PRDs/code into structured test cases much like Blue Codens does. Blue Codens' distinct piece is the automated Red Codens fix-PR hand-off — Autify's AI stops at healing tests, not producing app fix code.
- vs. mabl: mature auto-healing and native cross-browser support (Chrome/Firefox/Safari/Edge), plus Auto TFA failure triage into Jira/IDE. Blue Codens is narrower on cross-browser (Chromium/Firefox via Playwright) but closes the loop further — from triage to an actual generated and re-verified fix PR via Red Codens.

## Codens Suite

Codens is an AI development suite from Japan that automates the entire software development lifecycle — requirements (Green), implementation (Purple), code review & security audit (Orange), QA/E2E testing (Blue), and production error auto-fix (Red). Teams can build and operate software products without a large team of specialist engineers.

- Green (PRD) https://www.green.codens.ai
- Purple (implementation) https://www.purple.codens.ai
- Orange (code review & security) https://www.orange.codens.ai
- Blue (QA — this service) https://www.blue.codens.ai
- Red (auto-fix) https://www.red.codens.ai
- Auth (unified auth) https://auth.codens.ai

## FAQ

- What is Blue Codens? — An AI platform that generates test cases from specs/code/natural language, runs E2E tests with Playwright, analyzes failures into bug reports, and hands bugs to Red Codens for automated fixes, end to end.
- How does it auto-generate test cases and E2E tests? — Claude API structures test cases from your inputs; Claude Agent SDK + Playwright MCP autonomously explores the live app for exploratory E2E and extracts Playwright code.
- Does it support Playwright? — Yes, natively; tests run headless on ECS Fargate (Scale-to-Zero). Mobile is supported via an Agent proxy for Appium/Espresso/XCUITest.
- How much is automated through the Red Codens integration? — Detected bugs are forwarded to Red Codens, which generates a fix PR; Blue Codens re-tests it. The loop repeats unattended until green.
- How does pricing work? — 5-tier credit subscriptions, shared across the Codens family; see Key facts above.
- Do I need programming knowledge? — No for test design (natural language / spec input works); some technical knowledge helps for webhook/credential setup. Output is Playwright code.
- Does it integrate with CI/CD? — Yes, via a GitHub PR webhook; combines with GitHub Actions to run tests per PR and post results as status checks/comments.
- How is it different from Autify or mabl? — Both offer strong no-code authoring and AI-assisted healing/triage, but neither auto-generates the app-level fix code. Blue Codens' Red Codens hand-off closes that last mile.

## Links

- Help: https://help.codens.ai (llms-full: https://help.codens.ai/llms-full.txt)
- Sign up: https://auth.codens.ai/ja/signup (ja) / https://auth.codens.ai/en/signup (en)
- Login: https://auth.codens.ai/ja/login / https://auth.codens.ai/en/login
- Contact: support@corevice.com
- Japanese: https://www.blue.codens.ai/
- English: https://www.blue.codens.ai/en/
- Full content: https://www.blue.codens.ai/llms-full.txt