LLMs are evolving from single, monolithic systems into collaborative networks of specialized agents, each with its own role, knowledge, and perspective.

Remember when you could build products that didn't change under your feet every 5 minutes?

What if you could ask your visual data a question, and it showed you exactly what your model missed?

This talk dives deep into the pros and cons of codebase indexing for AI-powered tools...

We’ll show how to take a quantized open-weight LLM, load it directly into a browser with WebGPU — no server, no API call.

This talk explores how to elevate an open-source LLM to frontier-level performance. We’ll start with training-free methods — such as process supervision and outcome supervision — that can deliver up to 1.5-2x quality boost without modifying the model.

In this talk, Oren Yosifon explores practical methods to reshape base models themselves - from pruning and ablation to targeted tuning - to boost performance, reduce cost, and bypass common model limitations.

In this talk, we’ll walk through the practical process of transforming any website into structured, meaningful context that can power your LLM applications.

Most AI apps don’t fail because of bad models—they fail because they stop learning...

Slow inference, sky-high GPU bills, users complaining about latency—sound familiar? ...

Join us to discover how MCP-UI enables the new web, where users can access their favorite apps uniformly through any agent.

How can they let developers move fast with AI while still holding onto the hard-won practices of good platform engineering?

This talk introduces a pragmatic toolkit for context management, demonstrating how mastering these principles helps explain why an unwanted outcome occurred, how to correct it, and how to prevent it next time

In this talk, Shahar Polak shares a real-world case study from ImagenAI on building and deploying AI agents that tackle these exact challenges in production.

In a series of real-world application hacking demos I’ll demonstrate how developers mistakenly trust LLMs in generative AI code assistants...

What if your AI could think like a detective before searching?

In this talk, we’ll cover how to take image generation from personal use to a practical tool for developers in production - from choosing the right model and mastering prompt engineering to ensuring output quality.

In this talk, we’ll share how this system works end-to-end: UI patterns for contributors, heuristics for safe merges, approval flows, and rollout metrics.

In this talk, we introduce CAIR (Counterfactual-based Agent Influence Ranker), recently accepted at EMNLP 2025, and show how it helps developers answer this question at inference time.

This session covers practical know-how learned through painful production iterations: how to build validation frameworks that catch LLM errors before they reach users, architectural patterns for constraining problem spaces without losing effectiveness, and techniques for creating evidence-based reasoning that can be audited and improved systematically.

Fasten your mental seatbelts—we're rocketing through a rollercoaster ride unraveling the hidden biases of Large Language Models (LLMs).

Everyone is excited about conversational AI. Everyone is implementing their own chatbots, until they have to make a conversation behave in production.

This talk explores practical techniques for debugging LLMs, focusing on systematic troubleshooting methodologies and analysis approaches you can create yourself.

What are agents, and how can they be leveraged to revolutionize GenAI systems?