AI Engineer · October 12, 2026

Scheduled agents: separate future triggers, active sessions, and memory changes

video Agent Security AI Engineering Model Evaluation

Scheduled agents: separate future triggers, active sessions, and memory changes video thumbnail

Why it matters

This Managed Agents workshop combines scheduled execution, session fan-out, and a research preview for memory updates. Current deployment documentation makes an operational distinction: pausing a schedule suppresses future automatic triggers while existing sessions continue and manual runs remain possible. Per-run budgets are separate caps, not a lifetime spending limit. The memory preview is not evidence of safe or reliable autonomous improvement.

My takeaway: Test pause, manual execution, active-session interruption, and budget exhaustion separately. Use explicit time zones and check daylight-saving behavior. Version memory changes and replay independent evaluation cases before allowing them to affect later scheduled work.

Keep exploring

More curated notes connected through Agent Security 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.

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.