Different perspectives. One harness.
AI-generated testing perspectives, not human reviewers. Select a profile to explore its focus.
AIAI QA sub-agent
AI test manager
Modeled on Jason Arbon’s approach to testing: start with the customer’s intent, follow the consequential risks, challenge the evidence, and make the next useful action clear. Jay is an AI persona inspired by Jason Arbon, not Jason himself. His visual identity is a distinctive J-shaped character, not a human portrait.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Security sub-agent
Web-application security specialist focused on authentication, authorization, session safety, exposed data, dependencies, and practical vulnerability evidence.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
OWASP sub-agent
OWASP-focused security specialist who challenges access control, injection, insecure design, misconfiguration, vulnerable components, integrity, logging, and SSRF risks.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Accessibility sub-agent
Accessibility specialist focused on keyboard use, assistive technology, inclusive interactions, responsive access, labels, feedback, and barriers affecting disabled users.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
WCAG sub-agent
WCAG specialist focused on criterion-level evidence across perceivable, operable, understandable, and robust behavior, without overstating automated scan results as conformance.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Usability sub-agent
User-centered design and usability specialist focused on discoverability, task clarity, responsive behavior, interaction friction, visual hierarchy, and inclusive UX.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Compatibility sub-agent
Compatibility specialist focused on browser, device, viewport, operating-system, assistive-technology, and support-matrix evidence, with explicit coverage gaps rather than assumed portability.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Performance sub-agent
Performance specialist focused on user-visible latency, Core Web Vitals, payload and request cost, caching, API timing, scalability, mobile constraints, memory, and leaks.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Content sub-agent
Content and UX-writing specialist focused on page identity, clear copy, information architecture, credibility, navigation, status communication, readability, and content quality.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Localization sub-agent
Localization specialist focused on translation accuracy, locale formats, pluralization, truncation, bidirectional layout, cultural fit, regulatory copy, and recovery behavior across languages.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Data integrity sub-agent
Data-integrity specialist focused on agreement between rendered values, APIs, events, schemas, exports, storage, calculations, retention, and downstream state.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Forms sub-agent
Forms specialist focused on input contracts, validation, boundaries, state, submission, recovery, data quality, conversion barriers, and accessible interaction.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Error UX sub-agent
Error and recovery specialist focused on truthful status, clear messages, consistent severity, actionable recovery, safe logs, failure loops, and user trust.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Search sub-agent
Search-interface specialist focused on discoverability, query handling, suggestions, empty states, input accessibility, relevance feedback, and resilient result navigation.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
News & content sub-agent
Digital publishing specialist focused on article identity, readability, supporting media, metadata, context, advertising boundaries, and multi-device content behavior.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Landing pages sub-agent
First-impression and conversion specialist focused on value clarity, trust, navigation, calls to action, responsive composition, dead ends, and page credibility.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Checkout sub-agent
Checkout and payment specialist focused on order accuracy, address and payment input, trust, retry safety, pricing truth, completion, and conversion-blocking failures.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Shopping cart sub-agent
Shopping-cart specialist focused on line-item state, quantities, promotions, totals, inventory changes, persistence, accessibility, and safe transition to checkout.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Pricing sub-agent
Pricing and subscription specialist focused on plan clarity, comparison, currency and locale, hidden conditions, billing cadence, conversion paths, and truthful claims.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Privacy sub-agent
Privacy specialist focused on personal-data exposure, consent, tracking, collection minimization, storage and transfer, debug leakage, user expectations, and AI-specific privacy risks.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
GDPR sub-agent
GDPR specialist focused on lawful consent, personal-data exposure, international transfer, minimization, retention, security, data-subject rights, transparency, and accountability.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Cookie consent sub-agent
Cookie-consent specialist focused on prior consent, purpose and vendor choices, reject symmetry, preference persistence, withdrawal, tracking verification, and regional behavior.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
Legal policy sub-agent
Policy-content specialist focused on discoverability, internal consistency, versioning, contact details, user rights, actual-product alignment, accessibility, and credible presentation.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
AI-generated code sub-agent
AI-generated-code specialist focused on logic, boundaries, null and empty states, failure handling, API use, security, privacy, tests, code smells, state, and misleading AI shortcuts.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
AIAI QA sub-agent
AI chatbot sub-agent
Conversational-AI specialist focused on task success, conversation quality, state, memory, recovery, privacy, safety, injection, tools, latency, integration, and nondeterminism.
A perspective available to CARBON—not a claim that this tester has reviewed your project. Findings require execution evidence.
CARBON · AI Agentic Verification Harness
/carbon
Pro only. Jay ranks critical code, asks you to approve a property and budget, then verifies supported logic, searches for counterexamples, and produces an evidence-backed HTML report.
Usage, scope and examples →Generate context-aware AI persona feedback for the current work or a named app, API, screenshot, document or concept; use safe intent-led journeys when runnable and distinguish observations from simulated reactions.
Continuously expand coverage and investigate bugs until stopped or a limit is reached. Requires two separate human confirmations; durable state and protected live report; no automatic fixes.
Hunt bugs with stateful multi-step journeys and persona exploration, not just a static checklist.
Explain Free commands, inspect scope when requested, and suggest the smallest useful next assessment.
Create a disposable demo project, optionally with existing tests, and perform a first CARBON assessment.
Read or change project testing defaults and analytics preferences in a protected local settings page.
Connect Jira/Xray or TestRail, read external test and issue evidence, manage non-secret project overrides, and preview or explicitly approve guarded synchronization.
Show evidence-qualified CARBON activity, token/model usage, issues found and verified fixed, unit economics, command frequency, leverage signals, and optional user-baselined savings.
Open a screenshot-based map of one saved Free assessment, its checks and findings. Not a cross-build planning workspace.
Show the complete project-local CARBON quality record: test inventory, declared automation architecture, frameworks, durable pass/fail history and trends, findings, and human-qualified decisions.
Ask or record only the project-specific human decisions that can materially change CARBON confidence, readiness, risk, test selection, or release interpretation.
Create prompt-defined tests; locally convert TestRail, Xray, and other legacy suites; run evidence-gated bake-in; repair converted definitions; and visually manage intent CRUD.
Generate prioritized planned CARBON tests from discovered widgets, standard flows, code contracts, recordings, and custom or learned flows.
Generate, extend, review, and optionally execute a large categorized chatbot test suite from current conversation context and project artifacts.
Use the coding agent's local browser for classic CARBON browser workflows with no testers.ai account required.
Run a bounded risk-based assessment of a project or URL, including business value, stateful checks, persona exploration and an evidence-qualified report.
Continue the prior broad CARBON candidate pool with the next highest-value deferred tests without repeating the initial pass.
Test one named feature, flow, API or behavior with reproducible steps and evidence.
Run CARBON GEO and AI Search testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required GEO report.
Run CARBON Agent Readiness testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Agent Readiness report.
Run CARBON Functionality testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Functionality report.
Run CARBON User Interface testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required UI report.
Run CARBON User Experience testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required UX report.
Run CARBON Usability testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Usability report.
Investigate accessibility using source, keyboard, zoom, visual and dynamic browser evidence.
Run CARBON Privacy testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Privacy report.
Run CARBON Security testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Security report.
Run CARBON Load Testing testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Load testing report.
Run CARBON Stress Readiness and Recovery testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Stress readiness and recovery report.
Run CARBON Performance testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Performance report.
Run CARBON Networking testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Networking report.
Run CARBON State Integrity and Round Trips testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required State integrity report.
Run CARBON Reliability and Resilience testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Reliability report.
Run CARBON Compatibility testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Compatibility report.
Run CARBON Content testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Content report.
Run CARBON Data Integrity testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Data integrity report.
Run CARBON API testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required API report.
Run CARBON Internationalization Readiness and Completion testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required INTL readiness and completion report.
Run CARBON Localization and Internationalization testing against a named feature, reachable target, API, source, screenshot, or current project and generate the required Localization report.
Run a bounded durable test-fix-retest validation loop.
Create isolated copies, inject controlled faults and error conditions, verify recovery, and prove the originals remained unchanged.
Upgrade existing tests with sparse model-powered screenshot quality checkpoints or deterministic local validation.
Run an intent-first confidence investigation loop: prioritize consequential questions, investigate and challenge, reassess evidence, then reprioritize within budget with a live decision audit.
Initialize a durable confidence-engineering workspace.
Map AI-system risks, claims, and decision-changing evidence.
Design, run, and analyze decision-relevant AI evaluations.
Independently challenge AI changes and their evidence.
Decide whether an AI release should ship, canary, hold, or roll back.
Contain an AI incident and preserve durable regression evidence.
Challenge evaluation populations, cases, and oracles.
Independently synthesize release evidence and uncertainty.
Review AI trust boundaries, data, tools, and side effects.
Find overclaims, weak evidence, and confidence theater.
Review AI evaluation statistics and supported inference.
Start with /carbon: a bounded, risk-based assessment with real execution evidence. Choose Pro when you want ongoing discovery, deeper specialists and team workflows.
Runs inside your coding agent, locally by default.
Scoped by your budget. Consequential actions need approval.
No project yet? Start with /carbon-demo.
In Claude Code, Codex, and other coding agents, default CARBON tests use your agent’s configured model access. Signed in with an eligible subscription? CARBON uses that allowance. Using API credentials? API billing applies.
Local storage ≠ local-only AI. Local runs keep files, evidence, and reports in your workspace. Your coding agent may send code, screenshots, and other context to its model provider.
Plan limits and extra-usage charges still apply. CARBON Pro licensing and CARBON Cloud are separate. Optional direct-model checks and external integrations can have separate costs and data flows. Command-usage analytics vary by edition—review its privacy policy and settings. Local does not mean offline or air-gapped.
Check /status in Claude Code or codex login status in Codex to confirm your billing route. A configured API key can select API billing instead of subscription usage. A standalone MCP client supplies the model access and execution tools; the MCP server does not include a subscription.
Provider documentation: Claude Code billing · Codex sign-in and billing.
CARBONILLUSTRATIVE EXAMPLEConfidence judgment
Evidence strength, not release probability.
Retry can lose the cart.
A stale total survives reload.
Verify recovery across two tabs.
INSIDE YOUR AI CODING AGENT
Choose your workspace: use CARBON in Claude Code or Cowork, or get CARBON Studio Lite for Codex (free, v0.1.12). For the native visual workspace and advanced testing, choose CARBON Studio Pro. Paid binaries are delivered separately to licensed customers.
Real testing, real evidence. Choose a useful assessment today—or an ongoing quality system for your team.
Free · no account required
A complete, bounded assessment inside the coding agent you already use.
Use it at work. No run quota or hidden findings.
Uses your agent’s existing model access; its plan limits or API charges apply.
Compare paid plans below
Continuous coverage, deeper investigations and your team in the workflow.
See current pricing and plan details. Questions before choosing? Email jason@testers.ai.
CARBON Light is MIT open source on both Claude and Codex. The separate Codex Studio Lite package is also MIT open source. Pro is commercially licensed. CARBON Cloud is a separate service.
Choose a plan for testing inside your AI coding agent. Compare the current prices and plan details below, then continue securely with Stripe.
Your coding agent’s model access and usage limits still apply. CARBON Cloud and CARBON Private Cloud are separate offerings, not included with these harness plans.
Free maps the pages, checks and findings in your current assessment. Pro adds a persistent workspace to compare builds, retain priorities and guide the next investigation.
/carbon-map opens the map for your project. Captures show what was observed—not proof that every behavior passed.
Expand the captured example →Pro team integrations · separate Cloud service
Steer cloud testing toward what matters: the user journeys, business risks and questions that deserve attention.
Choose features, checks, personas and test cases. Add the context that makes the investigation useful.
Review the findings and use the report to guide your next pass.
Cloud execution is separately configured. Enterprise/private-cloud availability and capacity are agreed with the team; installing the local plugin does not provision cloud workers or upload your project.
Sharing artifacts, using external services and paid execution require explicit approval.
Discuss cloud steering with the team →
A ready-to-present, 11-slide introduction for developers, testers and team leaders. Covers how CARBON works, the AI sub-agents, example commands, and optional expert testing support from Iceberg QA. Includes speaker notes and a presenter guide.
An alternative presentation led by Iceberg QA’s human expertise, with CARBON as the supporting toolkit.
CARBON PRO · /proof
Ask Jay which rules matter most, then verify one with /proof. Rank critical code by impact, approve the exact property and budget, and get a CARBON HTML report with checked evidence or a concrete counterexample.
Start with supported pure Boolean Python logic, including access-control decisions. Use exhaustive verification or the Lean model backend with independent checking. Every result states its scope, assumptions and freshness.
See /proof, examples and result states → · Available in Pro, not Light/Lite.