AI Engineer · November 3, 2026

Agent workflow graphs: test explicit branches and preserve decision provenance

video AI Engineering Model Evaluation Agent Security

Agent workflow graphs: test explicit branches and preserve decision provenance video thumbnail

Why it matters

Zachary Blumenfeld demonstrates compiling policies and recorded agent runs into an AIP procedure with scripted steps, decision points and explicit routing. The public fictional loan example links outcomes to cited records and procedure revisions, while exposing review pauses. Its small demonstration is not a validated lending system or a general accuracy benchmark; the compiled procedure only covers the behavior encoded in it.

My takeaway: Compare compiled rules with their source policy. Test approval, rejection, missing evidence and escalation, including cases absent from the source traces. Verify that only an authorized human can satisfy a human-only gate. Record inputs, overrides and the procedure revision, then replay tests after policy changes. Isolate procedural scripts and scope their permissions; a validated graph does not sandbox its code.

Keep exploring

More curated notes connected through AI Engineering and Model Evaluation.

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.