AI Engineer · October 26, 2026

Managed agent handoffs: separate conversation state from workspace state

Managed agent handoffs: separate conversation state from workspace state video thumbnail
Why it matters

Jack Wotherspoon’s Gemini Managed Agents walkthrough separates interaction history from the sandbox filesystem. A research agent writes an artifact that later agents read using the same environment identifier and fresh conversation contexts. The talk also describes proxy-injected credentials. The demo establishes a workflow pattern, not a security guarantee or verified investment forecast.

My takeaway: Prototype handoffs with synthetic data: have one agent write a versioned artifact, then start a fresh interaction in the same environment and check what persists. Validate artifact contents before downstream use. Test access boundaries and cleanup; keeping a secret outside the sandbox does not prevent misuse of authorized API calls.
Keep exploring

More curated notes connected through AI Engineering and Agent Security.

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.

OECD.AI Wonk · guide

A five-step roadmap to closing the AI evaluation gap

The roadmap addresses evaluation results that overstate real-world performance or fail to transfer across deployment contexts. Its five steps balance standardized and local tests, evaluate throughout the lifecycle, build qualified assurance and communication capacity, tailor tests to each value-chain actor and technology, and use a coordinated, trusted process for updating methods.

OWASP GenAI Security Project · tool

FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project

OWASP FinBot is a hands-on agentic-security CTF built around a simulated multi-agent financial-services platform with real tool access. Its challenges cover prompt injection, tool misuse, policy bypass, data exfiltration, privilege escalation, remote code execution, shared context, and compromised MCP servers.