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 skeptical pass on the story your evidence is telling.
Jason Arbon CEO, testers.ai
/carbon-skeptical-review
AIJasonAI Code ReviewAIFatimaError UX
“The model is reliable.” “Coverage is strong.” “The new version is
better.”
Those statements sound useful until you ask what they mean and what
would make them false.
/carbon-skeptical-review challenges AI-system claims,
evaluation plans, and release evidence. Its job is not to manufacture
doubt. It is to identify where the conclusion is stronger than its
support.
Ask what the summary left
out
An average improvement may conceal a severe failure in a small
customer group. A large sample may contain many variations of the same
easy question. A judge may reward the style of an answer without
checking whether it is correct.
The review asks how the evidence was selected, what assumptions it
shares with the implementation, and which missing observations could
reverse the conclusion.
It should also recognize strong evidence when it exists. Skepticism
that cannot say what would resolve a concern is not a useful testing
strategy.
Give it a claim to examine
/carbon-skeptical-review challenge the claim that this assistant is ready for all customers; identify unsupported generalizations and the evidence that would resolve them
The result should separate demonstrated contradictions, material
gaps, and lower-priority questions. It should connect each objection to
a decision rather than produce an endless list of theoretical
concerns.
This is especially valuable when a polished report is creating more
reassurance than the underlying observations justify.
You do not need the agent to be cynical. You need it to be precise
about what you know, what you do not, and why the difference
matters.
Install CARBON at testers.ai/carbon for a supported
coding agent such as Claude, Codex, or Cursor.
