Beta — 14-day free trial / 100,000 credits / no credit card required

From specs to
E2E tests, let AI run your QA.

Generate test cases from specs, code, or natural language and run them with Playwright. When tests fail, AI analyzes the bug and hands it off to Red Codens for an automated fix PR.

Start for free now See how it works
Spec → Tests
AI-driven structured test generation
Scale-to-Zero
Pay only for the E2E runs you use
Bug → Fix PR
Fully automated via Red Codens

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. As part of the Codens Suite, it hands detected bugs to Red Codens, which generates a fix PR and re-verifies it — fully unattended.

How it works

From test case generation to bug-fix hand-off, AI handles the entire QA loop

1

Ingest test sources

Provide a spec, PRD, code, or natural-language requirements. You can also pull PRDs directly from Green Codens.

2

AI test case generation

The Claude API produces structured test cases — steps, expected results, priority, and type (manual / automated / E2E) — in a single batch.

3

Exploratory E2E generation

Claude Agent SDK + Playwright MCP autonomously drives your app. By combining code analysis with live browser exploration, it extracts high-quality Playwright tests.

4

Run with Playwright

Tests run headless on a dedicated Playwright Worker on ECS Fargate. Scale-to-Zero means zero cost while idle, and SSE streams progress in real time.

5

Bug analysis & reporting

AI analyzes failure logs, screenshots, and console errors to produce a bug report with reproduction steps, root-cause hypotheses, and links to similar bugs.

Red Codens hand-off

Detected bugs are forwarded to Red Codens, which auto-generates a fix PR. Blue Codens re-runs the tests until the suite goes green — end to end.

Don't write tests — grow them

Most QA work — designing tests, implementing E2E, maintaining suites — is repetitive.
Blue Codens uses your specs and the live app itself as the source of truth, continuously updating your tests.
Your QA engineers can focus on what really matters: finding fragile spots and exploring user-facing risks.

Test-growing cycle
Input Specs / code / target URL
↓ AI test case generation + exploratory E2E
Build Auto-generate Playwright code
↓ Run on Fargate Worker (Scale-to-Zero)
Analyze AI bug analysis + reports on failure
Hand off to Red Codens → re-test

Key features

Test design, implementation, execution, analysis, and integration — all on one platform

AI test case generation

Generate structured test cases — including steps and priority — from specs, code, or natural language. PRDs from Green Codens can be linked directly.

Exploratory E2E generation

Claude Agent SDK + Playwright MCP autonomously drives a browser, discovers screen flows, and extracts Playwright test code using real selectors.

Automated Playwright runs

A dedicated worker on ECS Fargate runs your tests headless. With Scale-to-Zero, infrastructure cost during idle hours is zero.

Automated bug analysis & reports

AI parses failure logs, screenshots, and console errors to produce a bug report with reproduction steps, hypothesized causes, and similar-bug references.

GitHub PR-driven runs

A webhook fires when a PR is opened. Impacted tests are auto-selected and executed, and the results are posted back as a PR comment.

Quality metrics dashboards

Visualize test coverage, pass rates, failure trends, and average run times. Test gaps are detected automatically.

Red Codens integration

Forward detected bugs to Red Codens → fix PR generated → re-run tests. The QA-and-repair loop closes itself, end to end.

Jira / Issue Tracker integration

Bug reports are filed automatically in Jira, GitHub Issues, or Linear. Status syncs both ways, so the dashboard never drifts from reality.

Real-time progress over SSE

Test run progress, screenshots, and logs stream over Server-Sent Events. You always know which step is currently executing.

Get started in 4 simple steps

Integrates with your existing repos, PRDs, and issue trackers

1

Create an account

Sign up at auth.codens.ai. Create your organization and invite your QA team.

2

Upload your spec

Upload a spec, PRD, or codebase, or just point us at a URL. AI test case generation kicks off immediately.

3

Register your test target

Register the target URL and credentials, then launch exploratory E2E. Playwright tests are generated automatically.

✓

Enable PR-driven runs

Configure the GitHub webhook and every PR triggers automatic test runs, reports, and bug filings.

Example: live E2E run log

Test suite progress

login_flow.spec.ts PASS (3.4s)
signup_validation.spec.ts PASS (5.1s)
checkout_flow.spec.ts running…
invoice_export.spec.ts queued

Live Playwright output

▸ Spawning Fargate worker (chromium)…
▸ goto https://app.example.com/login
› fill[email] / fill[password]
› click "Log in"
✓ url == /dashboard
▸ goto /checkout
⚠ network 500 on POST /api/orders
▸ Asking AI to generate a bug report…
Real-time SSE streaming Auto bug reports on failure Auto hand-off to Red Codens

UI preview

Test suites, run results, and bug reports — all in one view

app.blue.codens.ai/projects/example/suites

Test Cases · checkout-flow

PASS 18 FAIL 2
TC-104 · E2E · Priority High
Dashboard renders after login
Last run 2 min ago · avg 3.4s
PASS
TC-117 · E2E · Priority High
Order confirmation does not return 500
Bug report BR-42 filed → handed off to Red Codens
FAIL
TC-118 · automated · Priority Mid
Coupons compute the correct discount
AI-generated (exploratory E2E) · not yet run
Not run
TC-099 · manual · Priority Low
Receipt PDFs render in the correct format
Manually verified
Manual OK

The 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.

The Blue × Red unattended loop

① Blue Codens detects a test failure
② Bug is auto-filed to Red Codens
③ Red Codens auto-generates a fix PR
④ Blue Codens re-runs tests to verify

Steps ①–④ repeat automatically, with no human in the loop, until the suite goes green.

Green
Requirements & PRD authoring
Purple
Implementation orchestration
Orange
Code review & security audit
Blue (this service)
QA / E2E test automation
Red
Production error auto-fix
Auth
Unified auth & org management (foundation)
See all of Codens →
www.codens.ai

How Blue Codens compares

Manual QA, running Playwright on your own, and AI QA platforms (Autify, mabl) — how Blue Codens differs

Note: information about competing products reflects each vendor's publicly available information as of July 2026. This is a general overview, not a definitive claim of superiority — features change frequently, so check each vendor's official site for the latest details.

Dimension Manual QA Playwright on your own Autify mabl Blue Codens
Test design source Written by hand Coded by engineers UI recording / natural language (Autify Nexus / Genesis) UI recording / conversational test planning Batch-generated from specs, PRDs, code, or natural language; PRDs can be pulled directly from Green Codens
E2E code generation None (manual verification) Playwright code maintained by hand Playwright-based, both code and no-code Primarily no-code Claude Agent SDK + Playwright MCP autonomously explores the live app and extracts test code
Handling failures Investigated and reproduced by hand Logs analyzed by hand "Fix with AI" auto-heals locators Auto-healing + Auto TFA triages failures into Jira/IDE AI auto-generates a bug report with reproduction steps, root-cause hypotheses, and similar bugs
Hand-off to a fix Manual ticket filing Manual ticket filing Ticket integration only (no automated fix PR) Jira/IDE integration only (no automated fix PR) Auto hand-off to Red Codens: fix PR generated → re-tested, closing the loop unattended
Cross-browser Possible manually Supported (you set up browsers/CI yourself) Supported, Playwright-based Native support for Chrome/Firefox/Safari/Edge Playwright-based, supports Chromium/Firefox (mobile via Appium proxy)
Operating model Scales with headcount; hard to scale Requires ongoing engineering maintenance No-code-first, easy for QA staff to run No-code-first, self-healing cuts maintenance Continuously updated from specs and the live app; runs without dedicated QA specialists

Blue Codens' biggest difference is that it doesn't stop at detecting a failure. Autify and mabl offer AI-driven locator auto-healing and failure triage/ticket integration, but neither generates the fix code for a detected bug. Blue Codens hands bugs off to Red Codens, closing the loop from detection → fix PR generation → re-test verification, fully unattended. Pulling test cases directly from Green Codens PRDs or natural-language requirements, and sharing credits across the whole Codens family, are further differentiators. On the other hand, mabl's breadth of native cross-browser support (Chrome/Firefox/Safari/Edge) and Autify's no-code ease of operation are real strengths of those products.

Subscription pricing

Flat monthly plans with included credit allowances. Top up overage with credit packs.

Test case generation, E2E test code generation, exploratory E2E runs, and bug analysis consume credits. Credits are pooled across the entire Codens family (Red / Blue / Green / Purple) at the organization level.

What are credits?

In Blue Codens, credits are consumed for AI-driven test case generation, E2E test code generation, exploratory E2E testing, and bug analysis reports.
Each plan includes a monthly credit allowance, and overage can be purchased via top-up credit packs.

Note: actual credit usage depends on spec size, the number of generated tests, and the depth of exploratory runs. Playwright execution itself does not consume credits.

14-day free trial · 100,000 credits · no credit card required

Free Trial

Try it out

¥0 / 14 days
100,000
credits (one-time)
No credit card required
Start for free

Hobby

For individual QA engineers

¥3,000 / month
300,000
credits / month
Up to 5 seats
Get started
Popular

Pro

For QA teams

¥10,000 / month
1,000,000
credits / month
Up to 10 seats
Get started

Business

For larger QA organizations

¥50,000 / month
5,000,000
credits / month
Up to 25 seats
Get started

Included in every plan

AI test case generation Exploratory E2E testing Automated Playwright runs Shared credits across the Codens family Audit logs

Enterprise (unlimited credits, custom contract, SLA) — reach out at support@corevice.com.

Hand the writing, running, and fixing of tests over to AI

Let Blue Codens handle test design, implementation, execution, bug analysis, and fix hand-off — and free your QA team to focus on exploration and value validation.

Start for free Contact us

14-day free trial • 100,000 credits • no credit card required

Contact

Questions, Enterprise plans / custom contracts, onboarding support — we'd love to hear from you

Email

We typically reply within 2–3 business days.

support@corevice.com

Other Codens products

PRD authoring, automated repair, and development orchestration — also worth a look.

Green Red Purple
Start your 14-day free trial (100,000 credits)

Frequently asked questions

About Blue Codens features, integrations, and pricing

What is Blue Codens?

Blue Codens is a platform that automates QA work with AI. It generates test cases from specs, code, or natural language, runs E2E tests automatically with Playwright, analyzes failures and produces bug reports, and hands bugs off to Red Codens for automated fixes — end to end. It is part of the Codens Suite and shares organization credits across the family.

How does it auto-generate test cases and E2E tests?

Provide a spec, PRD, code, or natural-language requirements, and the Claude API produces structured test cases — steps, expected results, priority, and type (manual / automated / E2E) — in one batch. For exploratory E2E, Claude Agent SDK + Playwright MCP autonomously drives the app, discovers real screen flows and selectors, and extracts Playwright test code. You can also pull PRDs directly from Green Codens.

Does it support Playwright? Which frameworks are supported?

E2E natively supports Playwright, and generated tests run headless on a dedicated Playwright Worker on ECS Fargate (Scale-to-Zero). Mobile testing is supported via an Agent proxy for Appium / Espresso / XCUITest. Run progress, screenshots, and logs are streamed in real time over Server-Sent Events.

How much is automated through the Red Codens integration?

When Blue Codens detects a bug from a test failure, it forwards it to Red Codens, which auto-generates a fix PR, and Blue Codens then re-runs the tests against that fix. The detection → fix → re-test loop closes completely until the suite goes green, so QA and repair run end to end.

How does pricing (credits) work?

Five-tier subscription pricing (Free 14-day trial / Hobby ¥3,000 / Pro ¥10,000 / Business ¥50,000 / Enterprise), each with a monthly credit allowance. Credits are consumed by test case generation, E2E test code generation, exploratory E2E, and bug analysis; Playwright execution itself does not consume credits. Credits are pooled across the entire Codens family (Red / Blue / Green / Purple), and overage can be topped up via credit packs. New sign-ups get a 14-day free trial with 100,000 credits and no credit card required.

Do I need programming knowledge to use it?

AI can generate test cases from just a spec, PRD, or natural-language requirements, so you can design tests without writing code. That said, initial setup — configuring the GitHub webhook, registering credentials for your test target — goes more smoothly with basic technical knowledge. Generated tests are output as Playwright code, so engineers can adjust them further if needed.

Does it integrate with CI/CD pipelines?

Yes — a GitHub PR-driven webhook integration auto-selects and runs impacted tests whenever a PR is opened, and posts results back as a PR status check and comment. Combine it with your GitHub Actions workflows to fold E2E tests directly into your CI pipeline.

How is it different from Autify or mabl?

Autify and mabl are strong at no-code test authoring and AI-driven locator auto-healing / failure triage, but neither generates the fix code for a detected bug. Blue Codens hands bugs off to Red Codens, closing the loop from detection to fix-PR generation to re-test verification, fully unattended (comparison based on each vendor's publicly available information as of July 2026; see the "How Blue Codens compares" section for details).