AAIF - Agentic AI Night
Agents in production
Agentic AI Night kicks off our Launch Series with what happens when AI agents move beyond the demo and into production?
We will explore what works in production, what breaks, the trade-offs, and the hard problems we’re still figuring out.
What to expect
Real production stories
Technical deep dives
Lessons from failure
Hard engineering trade-offs
Open discussion with fellow builders
Agenda
17:30 — Doors open & networking
18:00 — Welcome
18:15 - Main talk & demo
18:55 - Lightning talk
19:15 — Networking over food & drinks
Talk 1: Maturing MCP - by Phil Nash
MCP is a young standard, but its rapid adoption has put it under a level of scrutiny few protocols see. It's maturing quickly and we need to know what to expect as the protocol continues to change.
In this talk we'll look at where we've come from with MCP and where we're going. We'll take a look at the features added and deprecated in the latest spec consider the roadmap for the next period of development as MCP evolves and matures under the AAIF.
Lightening Talk 1: Multi-cloud X-ops agents - by Kieran Rimmer
A case study in agentic audit, observability, and remediation across multi-cloud environments.
Lightening Talk 2: Traces Are Not Enough: Measuring User Value for MCP Servers - by Ben Hudson
How do you know an MCP server actually helped someone when you never see the user, and your traces only capture tool calls – not whether the user got what they came for? In this talk, we'll walk through how you can answer that by building a user value loop system. In particular: why traces alone are misleading and the failure modes they don't surface, and what changes when engineering teams stop measuring "did the tool call succeed?" and start measuring "did the user succeed?"
Who Should Come
Come along to share something you’ve built, show a problem you’re working through, learn from others, or simply meet people exploring the same space.
Whether you’re building agents, enabling teams to build them, researching the underlying technology, or figuring out how to take agentic AI into production, you’ll find people here working on the same problems.
Bring questions. Bring something you’ve built — or something that didn’t work.
Building something worth sharing? Our CFP is now open.
About AAIF
The Agentic AI Foundation (AAIF) is a community dedicated to advancing the understanding and practical application of agentic AI. We bring together engineers, researchers, founders, builders, and AI enthusiasts to explore how autonomous AI systems are designed, evaluated, and deployed.
Through reading groups, workshops, and community discussions, AAIF brings together engineers, researchers, founders, and AI enthusiasts to exchange ideas, challenge assumptions, and learn from one another.
By attending, you agree to our Code of Conduct and Privacy Policy.