AI Engineer · October 25, 2026

Write an agent evaluation by defining one observable pass-or-fail criterion

video Model Evaluation AI Engineering

Write an agent evaluation by defining one observable pass-or-fail criterion video thumbnail

Why it matters

SallyAnn DeLucia’s workshop turns travel-agent traces into an evaluation dataset. It defines concrete success and failure criteria, selects the spans containing the required evidence, maps their fields into a judge prompt and inspects labels with explanations. Human annotations then check judge agreement. The exercise is a starting workflow, not evidence that automated scores are reliable by default.

My takeaway: Choose one behavior, such as respecting the requested trip dates. Write explicit pass and fail examples, select traces containing the necessary inputs and outputs, and map fields carefully. Label a held-out sample yourself, compare judge disagreements, and version the rubric. Use code for deterministic checks and keep separate metrics for separate requirements.

Keep exploring

More curated notes connected through Model Evaluation and AI Engineering.

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.

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.