Safer Agentic AIAuto-Assessor
Assess your AI systems against the Safer Agentic AI Framework. Upload your evidence documents and get AI-generated scores and gap analysis across all 16 safety suites.
Scores and remediation suggestions are AI-generated and indicative only. They do not constitute legal, regulatory, or compliance advice; verify results independently before relying on them.
Runs in your browser via WebGPU — no API key, but a ~5 GB one-time model download (Chrome/Edge 113+, Safari 18+). Cloud models available if you have a key.
Testing Ground
See how the auto-assessor works before committing. Browse pre-computed evaluation results using synthetic data from a fictional “Acme Autonomous Vehicles” company.
- •63 pre-computed results across all 16 suites
- •Scores from 1 to 5 with justifications and gap analysis
- •No API key or account needed
AI Safety Assessment
Evaluate your own organization's AI systems with live Claude analysis. Paste your evidence documents and get real-time scoring against any of the 994 evidence requirements.
- •Uses your own Anthropic API key — stored in your browser's session storage and cleared when you close the tab
- •Live evaluation with detailed justifications and gap analysis
- •Evidence is sent directly to Anthropic for evaluation, never to our servers. Data handling
How It Works
- 1Browse the 16 safety suites covering drivers (goals, values, security, transparency, governance) and inhibitors (deception, opacity, uncertainty).
- 2Select a sub-goal and review its Safety Functional Requirements (SFRs) and evidence requirements.
- 3Paste or upload evidence documentation and run automated evaluation against each requirement.
- 4Receive scores (1–5), justifications, identified gaps, and relevant excerpts for each criterion.