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.
Build chatbot cases around context, boundaries, and changing intent.
Jason Arbon CEO, testers.ai
/carbon-chatbot
AIDiegoAI ChatbotAIPetePrivacy / PII
The bot answered the opening question correctly. Then the user
changed a detail, asked a follow-up, and referred to something from six
turns earlier.
Now the test is interesting.
/carbon-chatbot generates risk-based chatbot suites from
the available conversation, product context, requirements, code,
policies, and existing tests. It can extend a suite without discarding
its history or execute it when that is requested and a suitable target
is available.
Give every case an
expectation
A useful case includes the persona, starting conditions, turns,
expected behavior, prohibited behavior, and evidence required. A factual
answer may have an exact oracle. A tone or usefulness judgment may need
a rubric or human review.
Imagine a support bot that explains refunds but cannot approve them.
Cases should investigate the difference between explaining policy,
collecting information, and claiming an action happened. Follow-ups,
contradictory details, unsupported requests, and recovery all
matter.
The agent should use confirmed product facts and identify uncertain
expectations rather than inventing policy to fill a spreadsheet.
Separate generation from
execution
/carbon-chatbot generate a suite for our refund assistant; include multi-turn corrections, policy boundaries, escalation, and unsupported-action claims
The HTML suite groups the cases for review and keeps them planned
until they run. Execution requires a reachable browser, API, or local
interface and appropriate permission, especially for paid calls or
effectful tools.
A large case count is useful only if the cases investigate materially
different behavior.
The goal is to find out whether the conversation remains helpful and
honest after the first easy answer stops being enough.
Install CARBON at testers.ai/carbon for a supported
coding agent such as Claude, Codex, or Cursor.
