Product family
AI Probe
Two products for quality engineering in the age of AI. AI Testing Probe brings your manual test cases into the system, learns from your team and automates them. AI Agent Probe tests your AI agents before they go live. In both, an expert approves every decision.
AI Agent Probe · maintenance assistant · run v4
- Knowledge base (RAG)95.4%
- Robustness97.6%
- Safety (jailbreak)100%
- Hallucination93.9%
- Accuracy89.5%
- KVKK18.2%
18,010 cases · 17 categories91.8%
Products
Learning test engineering
AI Testing Probe
Imports your manual test cases, learns from your team’s approvals, keeps improving prompt quality and automates the cases.
- Import manual test cases into test management
- A rule and prompt library that learns from approvals and rejections
- New test cases drafted from requirements
- Web, desktop, mobile and API automation
AI agent evaluation
AI Agent Probe
Evaluates chatbots and AI agents for accuracy, safety and quality with thousands of test cases generated from your own documents.
- A golden test set generated from approved documents
- 17 test types across 3 layers
- Reasoned scoring by an independent AI judge
- Agent regression that reruns on every release
Where to start?
You have thousands of manual test cases and automation is moving slowlyAI Testing Probe organizes them and moves them to automation through a learning workflow.
You are taking a chatbot or AI agent liveAI Agent Probe proves the agent answers accurately, safely and in line with regulation.
A shared core: you stay in control.
Both products run on the same governance layer and are deployed in your own cloud environment. Your data is never used for model training; the AI works only with approved context.
Workflow and traceability
Routing, approval state, traceability from requirement to result, and an audit trail.
Data and access
Personal data masking, least privilege, secret management and access to the test network only.
Model and cost
A model service in your own environment, pinned model versions, a cost cap and a reporting view.
Capabilities ready to use today
Every capability in the AI Probe family is ready to deploy. Risky decisions are not rolled out before they pass an acceptance gate.
| Capability | Product | Status | What it delivers |
|---|---|---|---|
| Agent evaluation with AI Agent Probe | AI Agent Probe | Ready | Versioned quality, safety and regression checks; failure clustering. |
| Manual case import and a learning library | AI Testing Probe | Ready | Standardizes existing cases and links them to requirements; learns from approvals and rejections. |
| Test case generation from requirements | AI Testing Probe | Ready | Faster case drafting; positive, negative and boundary coverage with traceability. |
| AI-assisted automation development | AI Testing Probe | Ready | Framework-aligned code generation and maintenance; review through pull requests. |
| Failure classification and clustering | AI Testing Probe | Ready | Separates environment and data failures from real application defects and flaky tests. |
| Locator repair suggestions | AI Testing Probe | Ready | Reduces locator maintenance; assertion changes remain defects. |
| Test management and Jira connections | AI Testing Probe | Ready | Automatic transfer of approved cases, run results and defects; a Jira ticket from every failed run. |
| AI-assisted exploratory testing | AI Testing Probe | Ready | Explores paths outside the scripted cases and passes findings to expert review. |
| Risk-based regression selection | AI Testing Probe | Ready | Selects the riskiest regression set for a change; switched on once it catches at least 95% of the defects of a full run for 4 sprints. |
Proven in the field: a maintenance assistant in the beverage industry.
An AI agent working with production line maintenance documents was tested with AI Agent Probe before go-live.
- 18,010
- test cases generated automatically from more than 60 technical documents
- 17
- test categories across the accuracy, safety and quality layers
- 91.8%
- pass rate in the first evaluation; the agent was found fit for go-live
- ~98%
- in the final pre-go-live run, after the issues found were fixed
Let’s decide together which product to start with.
Are you testing an AI agent or speeding up test automation? Let’s find the right starting point in a 30-minute call.