How Far Should an AI Agent Be Allowed to Go?
An evening for people building, shipping, and scaling with AI. In this hands-on session with Adeuk, we gave an AI agent real tools, increasing autonomy, and a series of increasingly difficult assignments. What happens when it tries to access restricted data? Exceeds its authority? Takes an irreversible action? Finds a creative path around the rules?
From recent meetups
How the night runs
- 6:00 PM Networking, food, and some dangerous ideas · meet other builders and propose challenges for the agent
- 6:30 PM The Agent Gauntlet with Adeuk · red-team the agent and the policies, review what executed, what was stopped, and why
- 8:00 PM Surviving production · open discussion
Get the recap, and the next event before it sells out
Slides and links from tonight's talks land here Thursday. Subscribers get the recap first, and an invite to next month's Boston meetup before the public Luma drop.
The AI Runtime newsletter
Production lessons from AI practitioners. New issues every week.
Read by AI practitioners at IBM, Amazon, Meta, Google, Nvidia, OpenAI, MIT, Harvard, and more for production learnings.
Free. No spam. Unsubscribe in one click. See past issues →
Prefer just the calendar? Subscribe to the Boston meetup on Luma → or add our events to your calendar (.ics).
Read before the talks
Get the background for tonight's topics from our own writing: weekly issues on Vertical AI Agents, Model Reliability Engineering, and the gap between AI demos and production.
The AI Runtime Field Guide
A guided reading path through The AI Runtime for AI practitioners. AI engineering, Model Reliability Engineering, and vertical agents, in the order that builds real production intuition. Free, no email required.