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.
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.
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.
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.
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.
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.
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.
AI
Virtual AI tester
Priya
Shopping Cart Tester
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.
AI
Virtual AI tester
Mateo
Pricing Page Tester
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.
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.
Keep the original failure in view while the code changes.
Jason Arbon CEO, testers.ai
/carbon-auto
AIJasonAI Code ReviewAIFatimaError UX
The agent finds a bug, changes the code, and runs something green. Is
the bug fixed?
Only if the new evidence actually addresses the original failure. It
is surprisingly easy to lose that connection when a conversation moves
quickly.
/carbon-auto runs a bounded CARBON validation loop. It
keeps the cycles, failures, repair proposals, and retests connected
instead of treating each turn as a new story.
Rerun the reproduction first
Suppose a saved preference disappears after reload. The agent
identifies a persistence problem and proposes a repair. After you
authorize the change, the first check should be the original
save-and-reload sequence. Neighboring checks come next: rejected saves,
account boundaries, and whatever else the change plausibly affected.
A different passing test does not close the finding. Nor should the
agent weaken the assertion until the implementation looks
successful.
The default loop stops at five cycles, 60 minutes, or two consecutive
clean cycles, whichever comes first. You can ask for tighter limits.
Clean cycles describe the tested scope; they do not establish a
defect-free product.
Keep authority explicit
/carbon-auto investigate settings persistence for two cycles; propose repairs and ask before changing code
The command does not grant automatic permission to edit the product,
buy services, publish changes, or perform destructive actions. A blocker
may be the correct reason to stop.
What you get is a durable account of progress: what failed, what
changed with approval, what was retested, and what remains. That is much
more useful than a final message that simply says “fixed.”
Install CARBON at testers.ai/carbon for a supported
coding agent such as Claude, Codex, or Cursor.
