Synthetic data plays an important role in the news ecosystem. Publishers are now monetizing a synthetic version of their data to help feed news-hungry agents in the wild. We discuss how grounded synthetic news data not only protects publishers against copyright infringement, but also reduces hallucination rates for broad agents built to use hundreds of tools. As agents become better and better generalists, the data that they retrieve via tool-use needs to be packed up and ""Context Engineered"" for quality and ease of consumption. The ancient adage was never more relevant ""Quality in -> Quality out"". Enter the world's largest news knowledge graph. A perfectly searchable, highly accurate, news context delivery machine - geared for high-stakes decision making agentic tasks far and wide. Some tasks include fact-checking, geopolitical risk analysis, event forecasts for prediction markets, and much much more.

Voice agents are increasingly handling our most sensitive data, from healthcare records to financial information. We inherently trust voices more than text; a psychological bias that creates a unique responsibility: we must design voice agents that honor the trust users naturally place in them. This talk explores how thoughtful design choices shape responsible voice AI deployment. We'll examine how interface design affects meaningful consent, how conversation flows impact privacy, and how voice patterns influence trust. Drawing from real-world examples, we'll cover practical design principles for voice agents handling sensitive data. As voice becomes the primary interface for AI systems, getting these design fundamentals right isn't just good UX, it's an ethical imperative.

In this talk we will bring to light the open secret in the AI community: most agents don't work reliably. We'll explore the most common ways agents fail, highlighting how fundamental issues with the model often can't be overcome with prompting. If this is true, then why aren't we correcting the paths in the model? Reinforcement learning offers the most promising path to reliable agents. Designing reward signals is the future of agentic development. In the next few years we will transition from agents that are programed deterministically, to agents that are taught interactively. We don't need to be stuck in the ice age of frozen models, we can take our agents to the next level of success.

If you’re an engineer building AI Agents, you probably know how hard it is to consistently improve them. But I think it’s not that hard—if you have the right mental framework to solve the problem. That framework is Eval-Driven Development—a fancy way of applying the scientific method to building ML systems. Fundamentally, it’s about iterating on ML systems using science (EDD) rather than art (vibe checks). In this session, we’ll explore how one can use the ideas of experimentation and evaluation to improve any AI agents consistently. We’ll also learn how to use LLMs as effective proxies for human judgment (evals) and build a data flywheel for improving its alignment, choose the right metrics, and set feedback loops from production to identify and improve long-tail scenarios.

Evaluating LLM performance is vital to successfully deploying AI to production settings. Unlike regular machine learning where you can measure accuracy or error rates, with text generation you're dealing with something much more subjective, and need to find ways to quantify the quality. As we combine LLMs together and add other tools in the agentic context, this becomes even more challenging, requiring robust evaluation techniques. In this talk I propose an approach to this evaluation that borrows from academic evaluation - namely, creating clear rubrics that spell out what success looks like in as close to an objective fashion as possible. Armed with these, we can deploy additional tested LLMs to conduct evaluation. The result is highly efficient and solves much of the evaluation dilemma, although there are still gaps that I will also discuss. (This is an adaptation of an article I wrote: https://towardsdatascience.com/evaluating-llms-for-inference-or-lessons-from-teaching-for-machine-learning)

Hi, I'm Dex. I've been hacking on AI agents for a while. I've tried every agent framework out there, from the plug-and-play crew/langchains to the "minimalist" smolagents of the world to the "production grade" langraph, griptape, etc. I've talked to a lot of really strong founders who are all building really impressive things with AI. Most of them are rolling the stack themselves. I don't see a lot of frameworks in production customer-facing agents. I've been surprised to find that most of the products out there billing themselves as "AI Agents" are not all that agentic. A lot of them are mostly deterministic code, with LLM steps sprinkled in at just the right points to make the experience truly magical. Agents, at least the good ones, don't follow the "here's your prompt, here's a bag of tools, loop until you hit the goal" pattern. Rather, they are comprised of mostly just software. So, I set out to answer: What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

What happens when AI agents stop just suggesting next steps – and start running the project? In this talk, Dr. Adam Sroka (CEO & Co-Founder, Hypercube) shares the learnings behind Jellyfish, an agentic AI platform designed to manage the end-to-end lifecycle of renewable energy assets and deliver 50% efficiency gains. Built to replace time-consuming, manual work done by project managers, analysts, and engineers, Jellyfish combines proprietary AI models with multi-agent workflows to automate planning, data collation, reporting, and real-time analysis – with human oversight built in. Adam will break down the system architecture, from workflow design and automation strategies to real-time analytics and user accessibility. He’ll also touch on the commercialization path, including IP considerations, and the broader role platforms like this will play in accelerating net-zero targets.

Agents are only as useful as the data they can access. EnrichMCP turns your existing data models, like SQLAlchemy schemas, into an agent-ready MCP server. It exposes type-checked, callable methods that agents can discover, reason about, and invoke directly. In this session, we’ll connect EnrichMCP to a live database, run real agent queries, and walk through how it builds a semantic interface over your data. We’ll cover relationship navigation (like user to orders to products), how input and output are validated with Pydantic, and how to extend the server with custom logic or non-SQL sources. Finally, we’ll discuss performance, security, and how to bring this pattern into production.