Reviewed 25 September 2026
Know what you’re evaluating.
A clear account of the product, its controls and the evidence available today.
| What it is | An agentic software testing and quality platform for engineering and QA teams. One quality lead coordinates approved checks and returns findings with inspectable evidence. |
|---|---|
| Product name | TestAgent is a working name. The repository and original sample assets use the internal label Tenhaw Quality. A final brand has not been selected. |
| Testing methods | Computer-use exploration, unit, API, Playwright, Gherkin, property-based and mutation testing. Execution is subject to the supported stack and qualified runner setup. |
| Repository connections | GitHub and Azure DevOps connectors are implemented. Repository permissions, source revision, supported suites and live execution readiness are checked during setup. |
| Agent interfaces | REST API, MCP tools and a CLI are implemented for authorised integrations. Scopes and approval rules continue to apply when an agent calls the product. |
| Human control | Teams approve the plan, targets, environment actions and run allowance. Human reviewers retain the release decision. |
| Evidence | Reports retain source identity, expected behaviour, actual outcomes, available artifacts and visible incomplete work. Supported findings can be reproduced and regression drafts reviewed. |
| Access and pricing | Evaluations are scoped with the team. Supported repositories, execution setup and price are agreed before testing starts. |
| Published proof | The owned local sample contains 19 task executions: 9 passed and 10 failed, with six mutation survivors. It uses deliberately seeded faults and contains no customer, model or cloud execution. |
| Current qualification | Implemented capability is distinct from a qualified live service. The provider, image, region, methods, data terms and approved environment must be confirmed for each evaluation. |
Inspect the supporting material.
The public sample includes its specification, source, executable tests and selected unchanged reports. The original product evaluation guide explains setup, execution boundaries, cancellation and export. Evaluation workspace access is arranged with the team; its sign-in paths belong to that workspace.
Read the original product evaluation guide ↗Common evaluation questions
01Can the AI testing team keep working overnight?
Yes. Set a schedule or watch selected branches to start approved checks automatically. Your configured runner, approved scope and spending limit govern each run. If setup, approval or allowance blocks testing, that stays visible for your team to resolve. Execution availability and support terms are confirmed during evaluation.
02What is an AI testing agent?
An AI testing agent helps plan and investigate software checks using your requirements and tools. This product coordinates an approved plan across multiple testing methods and keeps the results, evidence and unfinished checks available for human review.
03How does it work with our existing tests?
Repository inspection discovers supported existing suites and proposes a setup for review. Your team chooses the revision, requirements, methods and execution scope before approving a run. GitHub and Azure DevOps connectors are implemented; supported stacks and live runner availability are confirmed during evaluation.
04Can it test AI-generated code?
Yes. The testing workflow can investigate changes regardless of who wrote them. Its expectations should come from independently reviewed requirements, so generated code and generated tests do not simply repeat the same mistaken assumption.
05Does an agent decide when we release?
Your team makes the release decision. Passing, failing and incomplete checks remain distinct, and reports retain the findings and evidence gaps that matter to that decision.
06How can we evaluate it?
Request a walkthrough to discuss one repository or release, the expected behaviour and the methods you need. The team will confirm the supported setup, qualified execution environment, data handling and commercial terms before an evaluation starts.
07What does it cost?
Pricing is agreed for the scope of an evaluation. The walkthrough request carries no purchase commitment. Scope, run allowances and commercial terms are confirmed before paid work begins.
Meet your AI testing workhorse
Bring your toughest code.
Set your highest bar.
See how the AI testing team would challenge your next release. We’ll scope the methods, automation and evidence around your software.
Discuss an evaluation. No purchase commitment.