AI Security Resources
Guides, checklists and templates for building and securing AI agents, covering AI security and EU AI Act compliance. Direct download, no email and no form. They are yours to keep whether or not you ever contact us.
Practical techniques to prevent prompt injection attacks in LLM applications. Input validation strategies, output filtering patterns, and defense-in-depth approaches. Real-world attack examples with remediation.
Complete compliance framework for EU AI Act requirements. Risk classification methodology, documentation templates, human oversight protocols, and audit trail implementation. Ready-to-use checklists.
AI tooling we build and open-source
Classify AI systems by EU AI Act risk category. CLI + Python library with 65 tests.
50+ prompt injection attacks categorized by type with defenses and test tools.
Ready-to-use EU AI Act compliance templates. Annex IV, FRIA, risk management.
Generate Article 50 transparency notices. 7 types, 6 languages, CLI + library.
Why download our resources?
Written by the team that builds and secures production AI agents and automations with Claude Code. Every claim in them can be checked against the open-source code they are drawn from. We are not asking you to take our word for it: read the material and judge for yourself.