AI Engineer · September 27, 2026

Improving agent skills and memory through reviewed changes and task evaluations

video AI Engineering Agent Security Model Evaluation

Improving agent skills and memory through reviewed changes and task evaluations video thumbnail

Why it matters

Suraj Gupta’s publisher notes distinguish agents doing recurring work from agents proposing improvements to that work. Warp’s triage example turns human feedback into a skill-change pull request, while persistent memory retains investigation findings with editing and provenance controls. A separate evaluation loop compares models on recurring task classes. The demonstration does not quantify memory savings, and customer-facing routing evaluations were planned rather than available in the account.

My takeaway: Require review and version history for changes to reusable skills. Store the source and scope of each memory, support correction or deletion, and compare routing choices on your own tasks. Check provenance links and regression performance before allowing an improvement to affect later runs.

Keep exploring

More curated notes connected through AI Engineering and Agent Security.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.

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.