Your AI Agent Is a Distributed System

Most AI agents are introduced as a loop: think → call a tool → observe → repeat.

That model works beautifully in a demo. Then the process crashes halfway through a task. A tool times out after performing the operation. Two workers pick up the same job. The model retries a non-idempotent action. A deployment happens while an agent is running. Or an hour-long task fails at minute fifty-seven and starts again from scratch.

At that point, the interesting problems are no longer LLM problems. They are distributed-systems problems.

This session looks at production agents through that lens. We will map familiar concepts—queues, leases, heartbeats, idempotency keys, checkpoints, durable execution, retries, cancellation and recovery—onto real agent architectures.

The goal is not to turn every agent into Kubernetes. It is to identify exactly where classical distributed-systems thinking becomes necessary once an agent moves from a synchronous demo to software expected to run reliably for minutes, hours or days.

By the end, the audience should be able to look at an agent architecture and immediately identify where it can duplicate work, lose progress, corrupt state or fail unrecoverably.

Target audience: Backend engineers, platform engineers, AI engineers, architects and anyone shipping agents beyond prototypes.

Preferred duration: 35–45 minutes. Can be adapted to a 20-minute condensed version.

Technical level: Intermediate. Familiarity with backend systems is useful; no ML background required.

Format: Architecture diagrams, failure scenarios and implementation patterns. Optional live demonstration of an interrupted agent recovering from a checkpoint.

Product/vendor neutrality: The ideas apply across agent frameworks and model providers.

First public delivery: Available as a first public delivery for the selected conference/community.

Stop Giving Agents More Context

When an agent performs badly, one of the most common fixes is to give it more context.

Add more documentation. Retrieve more files. Increase the context window. Include more history. Attach the entire repository. Keep every previous tool result.

Eventually, the agent knows everything but understands nothing.

Large context windows have created the impression that context scarcity has disappeared. In practice, a different constraint remains: attention.

This session proposes a different architecture for agent context.

Instead of treating context as a bucket, treat it as a dynamically assembled working set: selected according to the current task, decision and stage of execution.

We will examine contextual scopes, progressive disclosure, retrieval boundaries, ephemeral tool outputs, repository navigation and strategies for letting agents fetch information when needed rather than carrying everything everywhere.

This session gives engineers a more useful way to think about the problem: not “How do I fit everything?” but “What does the model need to decide next?”

Target audience: Engineers building coding agents, RAG systems, autonomous workflows, developer tools or AI-assisted products.

Preferred duration: 35–45 minutes.

Technical level: Intermediate.

Format: Architecture patterns, failure examples and practical context-selection strategies.

Framework-independent: Applicable across coding agents, browser agents, RAG applications and tool-using systems.

Prerequisites: Basic familiarity with LLM applications is sufficient.

Incorporating AI into your products

A deep dive into making products smarter and more user-friendly by incorporating generative AI. This session takes you through identifying prime opportunities for AI enhancement, navigating the technical landscape, and ensuring ethical considerations. Learn how to leverage high-quality data, select the most effective AI models for your needs, and continuously refine these models for peak performance. Plus, discover how to seamlessly blend AI into your product's user experience, making it not just more intelligent, but also more intuitive and engaging.

AI In Production - Beyond Automation

This session will explore the transformative potential of AI agents and AI that goes beyond the mere basics of generations, such as chatbots and RAG. AI Agents are not just executing tasks but are evolving as autonomous entities capable of learning, adapting, and innovating. This session will delve into the groundbreaking frameworks like AutoGen that are pushing the boundaries of what AI can achieve
This session dives into real-world applications that demonstrate the potential of AI Agents to revolutionize everything from healthcare to finance and touches on how to build these.
It promises to challenge your perceptions and ignite your imagination about the future of AI

AI in Observability

This session will delve into the transformative potential of generative AI in shifting observability from a reactive to a proactive approach.

This session is crafted for IT professionals, cloud administrators, and developers seeking to advance their infrastructure management practices. The audience will be equipped with actionable insights on implementing a predictive, AI-driven observability framework that enhances both efficiency and system resilience.