Speaking
Talks, panels, and podcasts on agentic AI, post-AI-authored code, platform automation, edge systems, and applied security.
Talks
The slide decks are collected under Talks. A 15-minute showcase at swiss made software’s IT’s ABOUT TECH evening on the theme “Hand’s on software engineering was yesterday, now it’s AI — Really?”. Not a tool talk. A story about what changed for a long-time engineer after Claude Opus 4.5 and Claude Code arrived, and what happens to a backlog of years-old ideas when the bottleneck stops being time. Key takeaways: ModSecurity with the OWASP Core Rule Set (CRS) is a powerful open-source WAF, but tuning false positives remains painful and time-consuming. This talk introduced a self-learning approach that uses generative AI to analyze blocked requests, determine legitimacy, and automatically generate tuning rules, reducing manual effort while keeping humans in the loop for approval. Key takeaways: Media-friendly version: Using generative AI to automatically detect and fix WAF false positives, keeping ModSecurity effective without the tuning headache.I Stopped Writing Most of My Code
Self-Learning WAF: Using Generative AI to Tame ModSecurity False Positives
Available for
I am available for technical talks, panels, and podcasts on:
- Agentic AI Agent platforms, orchestration, context, tool use, governance, and observability.
- Post-AI-authored code What changes when AI writes most of the code: verification, review, tooling, and where the human moves.
- Platform automation Self-service infrastructure, workflows, and guardrails.
- Edge systems Reverse proxies, ingress, policy enforcement.
- Applied security Practical controls, incident response, operability.
- Open standards Sustainable architecture over vendor lock-in.