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.
A page can pass every obvious check and still fail the moment someone
uses it for a while.
Save a draft. Open another tab. Change accounts. Reconnect after a
timeout. Search for something you just deleted. These sequences expose
assumptions that a quick code scan or happy-path walkthrough may never
challenge.
/carbon-issues is CARBON's focused bug hunt. It combines
directed probes for common AI-code weaknesses with protected time for
open-ended discovery and confirmation.
Give exploration a real
budget
At least half of the entire run budget is reserved for executed
stateful, multi-step work and persona-led exploration, with at least a
quarter for each. Writing a persona description or waiting for setup
does not count as exploring.
Imagine a support worker trying to correct a customer record while a
background sync runs. The goal is not merely “click Edit.” It is to
finish a realistic task and investigate stale values, confusing
feedback, lost changes, and recovery along the way.
Code, product contracts, and previous evidence supply context. The
agent must not invent a requirement just to manufacture a bug.
Bring back
findings, not repairs you did not request
/carbon-issues hunt stale search results and account-switching problems in the local app; use isolated synthetic data; stop after 25 minutes
The report separates reproduced bugs, source-proven defects,
suspicions, and missing evidence. If setup blocks the protected
exploration, the report should say the allocation was not achieved.
The command does not automatically fix code or write to your issue
tracker. Its job is to give you actionable findings with a defensible
reproduction.
This is a testing strategy, not a claim that CARBON has measured
superiority over every coding agent. The advantage to investigate is
whether those deeper journeys reveal failures your normal first pass
never reaches.
Install CARBON at testers.ai/carbon for a supported
coding agent such as Claude, Codex, or Cursor.
