On AI Lounge since Nov 2026
Giselle Evita Koch
PaidMember #5,106DeveloperL2Security Engineer, Independent
Software engineer · AI agent security · Python, Java/Kotlin · Backend and application security · Copenhagen
How karma works. Everyone starts with 5. You get +1 each time another member upvotes one of your posts or comments (your own upvotes don't count), and lose it if they take the upvote back. Post what you're building, answer questions and help other members to earn more.
Achievements
Plugged In ×2Connected sources: GitHub, Hugging Face, LinkedIn, X, website.How: Connected 2 sources (GitHub, LinkedIn, X or a website) in Settings
Plugged In×2Featured
Shipper ×2Projects on your profile.How: Added 5 projects to their profile
Shipper×2
No posts yet
Giselle Evita Koch hasn't posted yet.
Pinned projects
Independent, reproducible checks of published AI-agent security claims, with re-runnable scripts
Block unsafe LLM agent tool calls before they run — OPA/Rego policy gate with approvals, DLP, and tamper-evident audit
ai-agentsai-security
fastapillm-securityopa
GitHub profile and portfolio index for AI agent security, authorization and evidence work.
ai-securitycloud-securitycompliance-automationllm-agentsopa
Enforceable AI security portfolio — a five-repo stack from vendor red-teaming to runtime agent policy enforcement
agent-securityai-securitygithub-pagesllm-securitypersonal-website
Superseded research benchmark; replaced by Agent Security Gate, which re-measures against AgentDojo.
ai-securityappsecbenchmarkingllm-agentsllm-security
Evidence-first AI vendor assurance and defensive agent testing with sanitized reports, fail-closed gates, OWASP/NIST mappings, and signed release provenance.
ai-security
fastapillm-evaluationllm-securityowasp
About
Software engineer · AI agent security · Python, Java/Kotlin · Backend and application security · Copenhagen
Stack
OpenAI Agents SDK
Qwen
Ollama
Claude
Kimi
Lovable
Gemini
Grok
ChatGPT
Cursor
Vercel
GitHub Copilot
DeepSeek
Supabase