The Future of Agentic AI: Architecting the Global Control Plane

Abstract

The agentic AI landscape is facing an architectural crisis due to framework fragmentation, bottlenecking the creation of truly reliable autonomous systems. 

This session pivots from individual agent design to the critical challenge of systems architecture and coordination, presenting the essential blueprint for a Global Agentic Control Plane. We will detail how this control plane enables disparate, multi-framework agents—operating across diverse networks, clouds, and regulatory regimes—to be dynamically orchestrated and reliably composed into collaborative teams. 

The session will dive into the core engineering hurdles, including cross-framework durability protocols, state management in a distributed world, and providing the necessary compliance and audit trails, offering a vendor-neutral, blueprint-level look at the architecture required for enterprise-grade Agentic AI.


Speaker

Tyler Jewell

CEO & President @Akka and a four-time DevEx CEO

With 30 years in development platforms, he’s led product teams at BEA, Oracle, Red Hat, and Quest. A lifelong DevOps advocate and investor (InfoQ, Sourcegraph, Cloudant, TheLoops.ai, SauceLabs, and more), he also curates the Developer-Led Landscape, a public database of 1,700 DevOps companies. Outside work, he’s a private pilot and volunteers with Angel Flights in Aurora, Oregon.

Read more

Session Sponsored By

Akka is used to develop resilient, low latency, large scale, cloud-to-edge distributed applications.

Date

Monday Nov 17 / 10:35AM PST ( 50 minutes )

Location

Pacific LM

Video

Video is not available

Share

From the same track

Session

AI won't fix developer productivity (unless you fix context first)

Monday Nov 17 / 01:35PM PST

AI coding tools promise productivity gains, but many teams aren’t seeing the impact.

Speaker image - Dennis Pilarinos

Dennis Pilarinos

Founder and CEO @Unblocked

Session

AI Native Architecture for Java Applications

Monday Nov 17 / 02:45PM PST

We are currently moving from "AI-enabled" systems, where artificial intelligence is an additive feature, to "AI-native" systems, where intelligence is the foundational, architectural core.

Speaker image - Pratik Patel

Pratik Patel

Java Champion and lead developer advocate @Azul Systems

Session

Building Zero-CVE Container Images at Scale: Patterns and Pitfalls

Monday Nov 17 / 03:55PM PST

Every team wants secure container images, but few realize how complex it becomes at scale.

Speaker image - Natalie Somersall

Natalie Somersall

Principal Solutions Engineer @Chainguard

Session

Develop and Deploy a Trustworthy Multi-Agent System (Live Demo)

Monday Nov 17 / 05:05PM PST

Agents are inherently unreliable. While simple to prototype, agentic systems with their many (distributed) moving parts are complex, have degrading trust, and are expensive due to inefficient model usage and ineffective scaling.

Speaker image - Tyler Jewell

Tyler Jewell

CEO & President @Akka and a four-time DevEx CEO

Session

Shift Left with Observability and AI Driven Development

Monday Nov 17 / 11:45AM PST

Developers today are not just writing code, they’re orchestrating complex systems, managing pipelines, and maintaining reliability at scale. But when observability starts too late in the lifecycle, teams are left reacting instead of building.

Speaker image - Sean  O'Dell

Sean O'Dell

Product Marketing Manager @Dynatrace