AI Engineer · October 24, 2026

Agent regression tests: track safety and task completion separately

video Model Evaluation Agent Security

Agent regression tests: track safety and task completion separately video thumbnail

Why it matters

Sofia Jakovcevic’s refund-agent example shows why an average score can hide a tradeoff: a prompt change improves action safety while reducing task completion. Her regression loop samples production traces, adds known failures and successful workflows, compares baseline and candidate runs, and gates changes on separate criteria. Demonstration scores are not a production effectiveness study.

My takeaway: Build a versioned dataset covering ordinary work, known failures, edge cases and successes to preserve. Compare baseline and candidate agents on the same cases with separate safety and completion checks. Review judge disagreements and repeated-run variation. Block release when a required dimension regresses, even if the average improves.

Keep exploring

More curated notes connected through Model Evaluation 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.

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.

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.