Building, Securing, and Scaling Real-World Agents
LIVESTREAM
4:00 PM - 7:00 PM GMT
December 8, 2026

Building, Securing, and Scaling Real-World Agents

Everyone is talking about AI agents. But what happens when you actually put them to work?
What happens when agents start collaborating across systems, handling sensitive credentials, making decisions in enterprise environments, and operating for hours or days without someone watching over their shoulder? Suddenly, building an agent is the easy part.
The real challenge is making it work.
Join the Agentic AI Foundation (AAIF) for a closer look at what it takes to turn agentic AI from promising experiments into systems that can operate in the real world. We're bringing together the people building these technologies to share what they're working on, what they've learned, and some of the challenges they're trying to solve.
And the topics go well beyond another conversation about prompts and models.
What does it actually take to build agents that work?
Bartosz Gonczarek (Vstorm) will take us somewhere unexpected: medical triage, where Agentic AI has reached 98% accuracy, exceeding an expert nurse panel. Gerardo Lopez (Veritas Automata) will show how collaborative AI agents can run natively on Kubernetes, using Kagent, Google ADK, and the A2A protocol. Meanwhile, Jiquan Ngiam (MintMCP) will explore the infrastructure behind AI coworkers that can work alongside teams, access enterprise tools, and retain context.
But what happens when things go wrong, or when you can't trust the other agent?
Yaron Schneider (Diagrid) will dig into building agents that survive failures, recover their state, and prove what they've actually done. Keith Perry (GoDaddy) will explore how agents can verify each other's identities in under a millisecond, even offline, before exchanging sensitive credentials.
And what does it take to make all of this work at enterprise scale?
Bob Van Osten (Salesforce) will share how Salesforce is building and deploying agents for real enterprise customers. Remy Thellier (Snowflake) will explore how tabular and relational foundation models could bring new predictive capabilities into agentic workflows. Imran Siddique (Opaque Systems) will tackle a different kind of security challenge: protecting model weights when they leave the environment where they were created.
And because getting agents into production is one thing, knowing whether they'll actually perform is another, Nikolay Dolgov (Independent AI/ML Engineer and Researcher) will challenge conventional evaluation assumptions, showing how a system calibrated for 90% coverage can fall to just 9–15% under distribution shift.
Different perspectives, different technologies, and very different challenges, all connected by one question:
What does it really take to build AI agents you can trust in the real world?
Come for the technical insights, stay for the ideas, and leave with a better understanding of where agentic AI is heading, straight from the people building it.
Less speculation. More engineering. More things worth learning from.

Speakers

Demetrios Brinkmann
Chief Happiness Engineer @ MLOps Community
Jiquan Ngiam
CEO and Co-Founder @ MintMCP
Keith Perry
Principal Software Engineer @ GoDaddy
Yaron Schneider
CTO @ Diagrid
Bob Van Osten
VP of Product @ Salesforce
Imran Siddique
Chief Platform Officer @ Opaque Systems
Nikolay Dolgov
AI/ML Engineer and Researcher @ Independent
Gerardo Lopez
DevOps @ Veritas Automata
Remy Thellier
Leading AI Partnerships @ Snowflake

Agenda

From4:00 PM
To4:10 PM
GMT
Tags:
Opening / Closing
Welcome & Announcements

Welcome, quick event overview, key announcements, and introduction to the first showcase session.

+ content:video.read_more_button
Speakers:
user's Avatar
From4:10 PM
To4:30 PM
GMT
Tags:
Presentation
Building the Infrastructure for AI Coworkers

MintMCP is building the infrastructure for AI coworkers: persistent agents that work alongside teams in Slack and Teams. We’ll demo how our platform combines MCP gateways, agent identities, scoped access, monitoring, guardrails, and memory to give agents governed access to enterprise tools and data. We'll show what it looks like when agents move beyond individual copilots to become AI teammates.

+ content:video.read_more_button
Speakers:
user's Avatar
From5:00 PM
To5:20 PM
GMT
Tags:
Presentation
Don't Trust. Verify. Sub-Millisecond, Offline, Agent Verification with ANS.

Your agents are about to run for hours with no human in the loop. Before one of them hands a credential to another, what proves the other side is real? This talk walks through the Agent Name Service, or ANS: a SCITT receipt anchored in a tamper-evident transparency log, an expiring status token, and a DPoP or mTLS proof that ties identity to OAuth 2.0. You'll leave knowing how to verify any agent, caller, or callee, offline and in under a millisecond, before anything sensitive leaves your hands.

+ content:video.read_more_button
Speakers:
user's Avatar
From5:40 PM
To6:00 PM
GMT
Tags:
Presentation
Building Failure-Proof Agents That Prove What They Did

AI agents fail in unpredictable ways: models time out, tools break, processes restart, and reasoning spans hours or days. This talk shows how to build agents that survive those failures without starting over - and produce verifiable evidence of every action they took. We’ll explore agentic durable execution and how it differs from legacy durable execution, persistent state, retries, cryptographic provenance, and patterns for building trustworthy agentic systems.

+ content:video.read_more_button
Speakers:
user's Avatar
From6:05 PM
To6:25 PM
GMT
Tags:
Presentation
The Goose Development Kit

For a long time, the goose agent has been available as a desktop application and command line tool. Our new vision for the project includes the Goose Development Kit (GDK). This new SDK for goose lets you embed the high quality goose agent in your own program and choose individual parts that are useful to you. In the doc I will cover the rationale for GDK, how to get started, and the kinds of things you can build with it.

+ content:video.read_more_button
Live in 21 days 16 hours
4:00 PM - 7:00 PM GMT
December 8, 2026
Online
Organized by
user's Avatar
Agentic AI Foundation
Live in 21 days 16 hours
4:00 PM - 7:00 PM GMT
December 8, 2026
Online
Organized by
user's Avatar
Agentic AI Foundation