AIRTA - AI Risk Testing Agent
Open source and free to use. The proactive engine of AIRTA Systems - specialized AI agents generate hundreds of reusable compliance test prompts and rigorously stress-test your AI products before they reach consumers.
AIRTA is open source: view it on GitHub.
What is AIRTA?
Open source and free: AIRTA is published on GitHub with no license fee. Run it locally or in CI, generate and execute test suites, and export results to AIRTA Systems - the tool itself costs nothing.
Proactive Risk Testing: AIRTA deploys specialized AI agents - Compliance, Strategy, and Business - that automatically generate hundreds of reusable test prompts tailored to your AI product and applicable regulatory frameworks.
Pre-deployment Assurance: AI components are stress-tested before and continuously during deployment, identifying vulnerabilities, scope violations, and compliance gaps before they reach end users.
Centralized Management: The internal AIRTA Portal aggregates all test results, reports, and remediation tasks in one place - the central nervous system of your AI safety programme.

Three Specialist Agents. One Unified Test Suite.
Compliance Agent
Maps your AI product against OWASP LLM Top 10, NIST AI RMF, GDPR, and sector-specific rules (e.g. FCA, MHRA). Generates safety-aligned test prompts and flags non-conformance against your chosen frameworks.
Strategy Agent
Simulates adversarial users, red-team scenarios, and edge cases. Stress-tests prompt injection, jailbreaks, scope creep, and excessive agency - capturing vulnerabilities before bad actors do.
Business Agent
Evaluates real-world consumer interactions for harm, bias, and misleading outputs. Ensures your AI performs safely under everyday usage patterns, not just synthetic test conditions.
What AIRTA Delivers
- Free and open source - Full test generation, execution, and reporting pipeline with no subscription required. Fork, extend, and run on your own infrastructure.
- Hundreds of reusable test prompts - generated automatically from compliance frameworks and your product specification.
- Pre-deployment risk reports - structured findings mapped to OWASP LLM Top 10, NIST AI RMF, and your chosen sector or regulatory frameworks.
- Continuous testing cadence - monthly or on-release cycles, not a one-off audit.
- Audit-ready documentation - every test, result, and remediation step is logged and exportable for regulator or notified body review.
- AIRTA Systems export - import pipeline results into your compliance programme via the bulk import API for review and audit workflows.
- Bi-directional AILP integration - live consumer incidents from AILP feed back into AIRTA for updated test coverage.
Built for Compliance as a Continuous Process
One-time audits are insufficient for AI products that update frequently. AIRTA treats compliance as an ongoing discipline - automating the test generation, execution, and reporting loop so your team can focus on remediation rather than administration.
Whether you are preparing for a conformity assessment, responding to a regulator, or onboarding a new AI component, AIRTA gives you a defensible, documented record of due diligence at every stage. Clone the open source repo on GitHub and get started for free.
Post-Market Monitoring & Continuous Testing
The EU AI Act, Product Liability Directive, and AI governance frameworks require continuous monitoring and testing after deployment. On AIRTA Systems, PMM is delivered in direct association with our subsidiary Genbounty, meeting continuous testing obligations through natively integrated Challenge Panels.
Three Continuous PMM Streams:
- Consumer Reporting: Managed resolution portal with timestamped, exportable incident threads
- Consumer Log Analysis (AILP): Live interaction scoring mapped to EU AI Act, PLD, OWASP, and NIST
- Genbounty Challenge Panels: Proactive human adversarial and agentic testing integrated directly into AIRTA Systems as one company
- Unified Evidence Package: Export audit-ready compliance reports for regulators, legal teams, and auditors
EU Product Liability Directive (PLD) & Litigation Defence
AI systems are legally classified as products, exposing providers and deployers to strict liability claims and regulatory fines up to €35M. Build your legal defence before an incident happens with an immutable record of continuous testing, monitoring, and remediation.
Shift the Burden of Proof in Your Favour:
- Documented Due Diligence: Every pre-launch test, post-market log, and remediation action is timestamped and traceable
- Continuous Testing Defence: Proactive post-deployment Challenge Panels via our subsidiary Genbounty prove ongoing safety verification
- Customer Feedback Loop: End-to-end consumer harm reporting and resolution required under the Product Liability Directive
- Court & Regulator Ready: Export structured evidence packages in PDF, JSON, or CSV for legal counsel and insurers
See how PMM supports Product Liability Directive compliance →
See AIRTA on your systems
Book a demo of the testing agent, or contact us about running it with the control center. Pair it with AIRTA Red Team and AILP when you are ready for the full loop.

