AI Test Harness

Fully automated QA subagents.

Add QA subagents

CARBON does the QA testing work. You take the credit.

Works with

Claude
Codex
Cursor
Antigravity
MCP agents

Test frameworks and suites

Vibium
Playwright
Selenium
Cypress
pytest
JUnit
Gherkin
Robot Framework
TestRail
Xray
Manual cases

One command

Fully automated—or tell CARBON exactly what you want.

Use /carbon by itself for the complete testing cycle—or add any testing request in plain language. CARBON turns it into a robust, repeatable system with evidence and confidence analysis.

More specialized commandsOptional

Current testerJason · Overall CARBON

/carbon

Complete testing cycle

Scope Test Evidence

Evidence-backed result

Ready0 / 3

Coding agent · jtest

Agent runtime

Current testerJason · Overall CARBON

/carbon

The default example uses published jtest/.carbon results. The natural-language example demonstrates how CARBON structures a request; specialized examples replay observed evidence or preserve explicit not-run boundaries instead of inventing passes.

AI testing sub-agents

A full cast of AI testing sub-agents.

CARBON routes the specialist sub-agent whose testing perspective fits the risk in front of you. Each sub-agent has a defined domain, concrete checks, and the same obligation to show evidence and limits—not just a generic testing prompt.

Sharon

Security Tester

Tests authentication, authorization, sessions, secrets, exposed data, dependencies, and practical vulnerability evidence.

Security

Jason

GenAI Code Tester

Challenges AI-generated logic, boundaries, null and empty states, failure handling, API use, security, privacy, tests, and misleading shortcuts.

AI Code Review

Alejandro

Accessibility Tester

Tests keyboard use, assistive technology, labels, feedback, responsive access, and barriers affecting disabled users.

Accessibility

Hiroshi

WCAG Compliance Tester

Gathers criterion-level WCAG evidence without overstating an automated scan as accessibility conformance.

WCAG

Mia

Usability Tester

Tests discoverability, task clarity, responsive behavior, interaction friction, visual hierarchy, and inclusive UX.

Usability

Tariq

Performance Tester

Measures latency, Web Vitals, payload and request cost, caching, API timing, mobile constraints, memory, and leaks.

Performance

Show the full cast15 more sub-agents

Sophia

Content Quality Tester

Reviews page identity, copy clarity, information architecture, credibility, status communication, readability, and localization.

Content

Richard

Forms Tester

Exercises input contracts, validation, boundaries, state, submission, recovery, data quality, conversion, and accessible interaction.

Forms

Fatima

Error Message Tester

Tests truthful status, clear messages, consistent severity, actionable recovery, safe logs, failure loops, and user trust.

Error UX

Mei

Search Box Tester

Tests query handling, suggestions, empty states, input accessibility, relevance feedback, and resilient result navigation.

Zara

News Content Tester

Reviews article identity, readability, supporting media, metadata, context, advertising boundaries, and multi-device behavior.

Publishing

Yuki

Homepage & Landing Page Tester

Tests value clarity, trust, navigation, calls to action, responsive composition, dead ends, conversion, and credibility.

Landing Pages

Hassan

Checkout Tester

Tests order accuracy, address and payment input, trust, retry safety, pricing truth, completion, and conversion-blocking failures.

Checkout

Priya

Shopping Cart Tester

Tests line-item state, quantities, promotions, totals, inventory changes, persistence, accessibility, and checkout transitions.

Shopping Cart

Mateo

Pricing Page Tester

Tests plan clarity, comparison, currency and locale, hidden conditions, billing cadence, conversion paths, and truthful claims.

Pricing Pages

Pete

Privacy Tester

Finds PII exposure, consent and tracking problems, excess collection, unsafe storage or transfer, debug leakage, and AI privacy risk.

Privacy / PII

Zanele

GDPR Compliance Tester

Tests lawful consent, minimization, retention, international transfer, data-subject rights, transparency, security, and accountability.

GDPR

Rajesh

Cookie Consent Tester

Verifies prior consent, purpose and vendor choices, reject symmetry, preference persistence, withdrawal, tracking, and regional behavior.

Cookie Consent

Sundar

Legal Policies Tester

Checks policy discoverability, consistency, versioning, contact details, user rights, product alignment, accessibility, and credibility.

Legal Policy

Marcus

OWASP Security Tester

Challenges access control, injection, insecure design, misconfiguration, vulnerable components, integrity, logging, and SSRF risk.

OWASP

Diego

AI Chatbot Tester

Tests task success, conversation quality, memory, recovery, privacy, safety, injection, tool use, latency, integration, and nondeterminism.

AI Chatbot

Enterprise private cloud

Run more tests in parallel—in your private cloud.

All local CARBON execution is free inside your coding agent. Enterprise can deploy CARBON Cloud inside infrastructure you control when selected work benefits from private parallel capacity, recurring runs, API automation, or a shared results console.

Keep the downloaded client local.

Install CARBON and use every local /carbon workflow for free. Project context, tests, credentials, evidence, and reports stay inside your coding-agent environment.

Add Enterprise private cloud.

Enterprise runs parallel workers, the API, and the web console in your cloud, VPC, or dedicated private instance. Your code, credentials, test data, and evidence stay within boundaries you control.

Run only approved workloads.

Use explicit planning, execution, results, import, and scheduling workflows. CARBON never silently moves a local run into your cloud environment.

See pricing Read Cloud setup details

CARBON pricing

Run everything locally for free.

The complete CARBON harness is free inside your coding agent. Enterprise adds high-volume parallel execution inside private-cloud infrastructure you control.

Local · Fully unlocked

All local execution · no card

Run the complete CARBON harness inside the coding agent you already use—for free.

Every local /carbon workflow
All specialist QA sub-agents
Bring your own model keys and test frameworks
Project-local plans, evidence, history, and reports

Add QA subagents

Enterprise

Custom

Your cloud or private instance

Run high volumes of CARBON tests in parallel inside your private cloud.

High-volume parallel test execution
Your private cloud, VPC, or dedicated instance
Private code, credentials, and evidence
Custom concurrency, integrations, and enterprise support

Local execution is fully unlocked and free. Private-cloud execution is Enterprise-only and explicit: CARBON never silently moves a local run into a cloud environment.

Browser and framework control

Native by default. Your framework when you want it.

By default, CARBON uses the browser and computer controls already built into your AI coding agent. If you want, ask it to use CARBON’s AI-first Clicky Browser, Vibium, Playwright, Selenium, or any other framework. CARBON can run, exercise, coordinate, and manage multiple test frameworks for you.

Default · fully automatic Native AI coding-agent browser and computer control

Run /carbon with no framework instructions. CARBON chooses the available native controls automatically.

Optional · just ask CARBON’s AI-first Clicky Browser—or any test framework /carbon use CARBON’s AI-first Clicky Browser

Optional framework choice

Ask CARBON to use Vibium.

CARBON handles Vibium behind the scenes, runs or creates the relevant automation, manages execution, and brings the evidence back into the same confidence analysis.

What you typeOptional

/carbon use Vibium for test automation

Framework managedTests exercisedConfidence analyzed

Optional framework choice

Ask CARBON to use Playwright.

CARBON can use the Playwright setup already in your project, create focused coverage when needed, exercise the suite, and manage the available traces, screenshots, assertions, and reports.

What you typeOptional

/carbon use Playwright for test automation

Framework managedTests exercisedConfidence analyzed

Optional framework choice

Ask CARBON to use Selenium.

CARBON can preserve your Selenium language and runner, manage the existing suite, add focused automation where needed, and bring available WebDriver results and artifacts into one evidence-qualified report.

What you typeOptional

/carbon use Selenium for test automation

Framework managedTests exercisedConfidence analyzed

FAQ

The practical questions.

CARBON stays inside your AI coding-agent harness, works with the tools you already use, records what it actually observed, and keeps missing evidence visible.

What does /carbon do?

By itself, /carbon runs the full testing cycle: it evaluates the project, target, and change; maps risk; creates the right tests; executes safe checks; collects evidence; and analyzes confidence with explicit limits and next actions. You can also add anything you want in plain language—what to focus on, which kinds of tests or frameworks to use, a particular flow, risk, environment, or constraint—and CARBON turns that request into a robust, repeatable testing system.

Can CARBON use my existing test frameworks?

Yes. CARBON can work with and control any classic test framework your coding agent can run, including multiple frameworks in the same project. It can help interpret, import, repair, and migrate tests between frameworks and implementation languages while keeping the durable test intent and evidence visible. Nothing is rewritten until you approve the change.

Can I use my own API keys?

Yes. CARBON can use the model and provider credentials already configured in your AI coding-agent environment. You keep control of those keys; CARBON does not require you to hand them to testers.ai.

Is CARBON private by default?

Yes. CARBON runs locally inside your AI coding-agent harness and writes its state and evidence to your project. testers.ai does not receive your code, prompts, test data, credentials, screenshots, or reports. We do not need or want your private data. Your chosen coding agent and model provider still handle data according to the configuration and terms you selected.

Which coding agents are supported?

The current packaging supports Claude Code, Codex, Cursor, Antigravity, and MCP-compatible coding agents. The same evidence boundaries apply regardless of host.

Can CARBON test more than browser UI?

Yes. Top-level testing covers functionality, UI, UX, usability, accessibility, privacy, security, performance, networking, reliability, compatibility, content, data integrity, APIs, and localization—when the required access and evidence are available.

Does a CARBON report mean everything passed?

No. Reports separate observed results from blocked, deferred, not assessed, and not measured areas. A completed-looking report is not treated as proof of untested coverage.

Who built this stuff?

People who have tested Chrome, Google Search, and Windows. These are products where quality has to survive relentless change and enormous scale. We built CARBON from that experience. We know how to make testing systems hold up when the pressure is real, and nobody cares more deeply about quality than we do. You can trust us to scale because we have already done it where scale is unforgiving. Quality is not a checkbox here. It is the whole point.

Who makes the release decision?

You do. CARBON assembles the evidence, severe findings, unresolved evidence gaps, and rollback context, but preserves human authority over ship, canary, hold, or rollback decisions.

Questions about CARBON?Ask about the plugin, testing workflows, privacy, frameworks, or anything else.