World Congress 2025 • Aug 20, 2025 • Session details

Compose the Future: Building Agentic Applications, Made Simple with Docker

Jim Clark , Mark Cavage , Tushar Jain , Yunong Xiao

Building agentic AI applications is now as simple as running standard containers. See how Docker Compose integrates models as top-level primitives to streamline your multi-LLM architectures.

Pause
Mute Enter Fullscreen
#1 about 4 min

Bridging application containerization and modern AI agent development

The historical shift of containerizing complex environments mirrors the current need to simplify scalable AI agent development.

#2 about 3 min

Defining core characteristics of autonomous AI agent systems

True agents autonomously manage control loops, connect securely to private data, and execute complex goals rather than basic tasks.

#3 about 3 min

Navigating multi-model infrastructures and compound agent swarms

Future agent workflows require mixing foundation models with specialized local variants to balance latency, privacy, and reasoning costs.

#4 about 4 min

Standardizing AI model and tool execution using containers

Packaging models as standard OCI artifacts enables frictionless discovery and execution of open-source resources directly within existing workflows.

#5 about 3 min

Centralizing tool access and observability with MCP Gateway

Utilizing a proxy architecture allows developers to scope server responses, filter tool access, and improve overall agent efficiency.

#6 about 3 min

Declaring full agent stacks structurally with Docker Compose

Treating models and tools as native declarative resources streamlines the composition and instantiation of complex multi-agent architectures.

#7 about 4 min

Architecting cooperating local agents for an ecommerce application

Combining distinct specialized task agents allows developers to parse customer sentiment and process database queries against locally hosted large language models.

#8 about 6 min

Bootstrapping a multi-agent application with generative code assistants

Utilizing inline coding prompt generation securely maps service dependencies and bootstraps execution models for immediate local testing.

#9 about 8 min

Offloading heavy inference workloads automatically to cloud GPUs

Shifting local execution to managed remote GPUs accelerates local development loops without requiring complex network configuration or data migration.

#10 about 3 min

Translating compose stacks natively into serverless cloud environments

Leveraging serverless compatibility ensures identical configuration schemas seamlessly deploy containerized agents as on-demand production services.

#11 about 8 min

Testing high concurrency loads against a serverless agent deployment

Provisioning distributed infrastructure on the fly ensures compound agent chains continuously respond reliably under thousands of concurrent application queries.

#12 about 4 min

Maximizing cloud native capabilities for scaling dynamic AI workloads

Serverless container compute natively supports stateful volumes, auto-scaling instances, and rapid GPU provisioning times for fast application serving.

#13 about 5 min

Automating vulnerability remediation and container builds using AI agents

Deploying dedicated autonomous workspace agents analyzes exposed vulnerabilities and continuously refactors pipeline code to optimize overall image security.

Matching moments

2:59 min

Adopting AI tools for developer container workflows

Ali Alp Ali Alp · World Congress 2026 Europe

2:22 min

Orchestrating local developer environments with AI tools

Angie Jones Angie Jones · World Congress 2025

2:31 min

Integrating generative AI into cloud-native applications

Cedric Clyburn Cedric Clyburn · World Congress 2024

1:14 min

Leveraging agentic capabilities and containerized developer environments

YK Sugi YK Sugi · World Congress 2025

2:37 min

Shifting to containerized AI deployment environments

Sebastian Rhode Sebastian Rhode · World Congress 2024

3:31 min

Practical learnings from deploying containerized AI solutions

Sebastian Rhode Sebastian Rhode · World Congress 2024

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 23, 2026 · 15:45–17:45

Stage 8

Docker's Agentic Platform: Sandboxes, MCP, and the Infrastructure of Autonomous Development

Oleg Å elajev

AI and Developer Relations at Docker

Oleg Å elajev
Open session

World Congress 2026 North America

September 23, 2026 · 13:15–15:15

Stage 8

The AI-Ready Developer Environment — Local Setup, Reproducibility, and Docker

Michael Irwin

Principal Engineer, Developer Success at Docker

Michael Irwin
Open session

World Congress 2026 North America

September 25, 2026 · 12:30–14:30

Stage 13

Docker sandboxes: protect your secrets, tokens, and personal data from AI agent mistakes

Kristiyan Velkov

Developer Relations Engineer at Zerops.io

Kristiyan Velkov
Open session

World Congress 2026 North America

September 23, 2026 · 10:45–12:45

Stage 8

SBX 101: Hands-on with Docker Sandboxes

Dan Ndombe

Staff Developer Success Advocate at Docker

Dan Ndombe
Open session

World Congress 2026 North America

September 25, 2026 · 10:20–10:50

Outdoor Stage

MicroAgents: The Microservices of the Agentic Era

Ashish Shubham

Runs the show bussiness at ThoughtSpot

Ashish Shubham
Open session

World Congress 2026 North America

September 24, 2026 · 17:30–18:00

Stage 6

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong