AI Red Team Engineering notes, research references, and field notes on AI systems, responsible AI, governance, and compliance.
Global search

Search AI Red Team

Search across the complete knowledge base.

Enter at least two characters to begin.
↑↓ select Enter open Browse the full research archive
Berkeley RDI · Event date August 1, 2026 - August 2, 2026

Berkeley Agentic AI Summit 2026

event past event Agent SecurityAI EngineeringModel Evaluation
Why it matters
August 1, 2026 - August 2, 2026
Event archive

Berkeley RDI's two-day Agentic AI Summit covers the full agent stack, from foundation models, infrastructure, and frameworks to evaluation, real-world deployment, safety, and security. The UC Berkeley program combines research and industry sessions and offers a public livestream.

My takeaway: Prioritize sessions that expose operational evidence: how agents receive identity and authority, how tool and memory boundaries are enforced, which end-to-end evaluations predict production behavior, and how failures are contained and replayed. Separate demonstrated controls from platform roadmaps and adoption claims.
Keep exploring

More curated notes connected through Agent Security and AI Engineering.

OpenAI News · framework

OpenAI’s Frontier Governance Framework

OpenAI's 22-page Frontier Governance Framework maps its frontier-model processes to California's Transparency in Frontier AI Act and the EU AI Act's general-purpose AI code. It documents lifecycle risk assessment, cyber-offense and other risk tiers, mitigation and residual-risk decisions, critical-incident handling, security risk management, model reporting, external review, responsibility allocation, and change control.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OECD.AI Wonk · guide

A five-step roadmap to closing the AI evaluation gap

The roadmap addresses evaluation results that overstate real-world performance or fail to transfer across deployment contexts. Its five steps balance standardized and local tests, evaluate throughout the lifecycle, build qualified assurance and communication capacity, tailor tests to each value-chain actor and technology, and use a coordinated, trusted process for updating methods.