YAAP (Yet Another AI Podcast)

Everything you need to know about harness engineering, in less than 30 minutes. In this episode, Yuval sits down with Mike Chambers from AWS to unpack harness engineering - the term that's quietly taken over the AI developer conversation. They dig into what a harness actually is (spoiler: it's everything outside the LLM), how it differs from context engineering and scaffolding, and why getting agents into production has been so hard. Along the way: MCP's rocky debut, OpenClaw's calendar-clearing chaos, and why multi-tenanted agent architecture is harder than it sounds - but doesn't have to be.

Chat was a great prototype. It’s a terrible product. In this episode, Yuval sits down with CopilotKit co-founder Atai to unpack why most agentic apps stall at “chat + vibes”, and why the real bottleneck in production AI isn’t models or reasoning. It’s UI. They break down what actually changed in the last year, why agents fundamentally break the request-response paradigm, and how a new generation of protocols is emerging to connect agents to real users. The conversation covers: AG-UI, Model Context Protocol (and MCP Apps) and Agent-to-Agent (A2A) Protocols The messy (but inevitable) transition from text-only chat to component-rich, voice-enabled, agentic applications. If you’ve built an agent that works but users still bounce, this episode explains why, and what the new “glue layer” of AI UIs is starting to look like.

Leaderboards reward “best average score.” Real users reward “answer fast, don’t hallucinate, don’t bankrupt me.” In this special deep dive episode, AI21’s CTO Barak Lenz walks through four gaps between what models can do and what real AI systems deliver: validation, contextualization (pick the right approach per input), latency (parallelize and stop early), and decomposition (making those choices continuously inside long workflows). Less “best model.” More “best execution.”

Tavily built a Deep Research Agent with production in mind. Something they could actually scale. So they did the unsexy work. They went through millions of agent logs, found where tokens were being wasted, and optimized each section of the system. The result surprised them: they cut token consumption by more than half (!), then tested quality and discovered they topped the DeepResearch Bench without even trying. In this YAAP episode, Yuval sits down with Dean from Tavily to break down how they built it, what they did differently from the usual top approaches, and which design choices made better results possible with far fewer tokens. What you’ll learn: How to reduce token burn without tanking quality Why reading millions of logs beats chasing the flashiest tech The design choices that pushed quality up while tokens dropped hard

Banks love GenAI. They just don’t trust it. Yet. In this episode of YAAP, Yuval talks with Renee Lau from AWS, a financial services industry specialist who works hands on with banks, insurers, and hedge funds as they try to move generative AI from pilots into production. Renee shares what she sees across the market, what actually works, and where teams get stuck. They explore the two sides of GenAI adoption in finance. Cost cutting back office automation and revenue driven use cases like hedge fund research. Along the way, they dig into compliance, pricing, human in the loop workflows, and the crawl walk run path to deployment. You will also hear why every bank believes it is a special snowflake, why that instinct is understandable, and how builders can still create solutions that scale across financial services.

Three years ago, it was just a house full of friends geeking out about AI. Today, it’s where researchers, founders, and engineers collide — and where hackathon demos turn into real startups. In this episode, Yuval sits down with Henry Yin, Co-founder & CTO of AGI House, to unpack how a pandemic project became the Bay Area’s builder epicenter. From fine-tuning meetups to venture funding, they trace the journey of turning one house into the heart of a movement.

Your LLM gave a great answer. But who decides what “great” means? In this episode, Yuval talks with Noam Gat about judge language models — reward models, critic models, and how LLMs can be trained to rate, rank, and critique each other. They dive into the difference between scoring and feedback, how to use judge models during inference, and why most evaluation benchmarks don’t tell the full story. Turns out, getting a good answer is easy. Knowing it’s good? That’s the hard part.

<p><b>RAG Is Not Solved – Your Evaluation Just Sucks</b></p><p>Your RAG pipeline is passing benchmarks, but failing reality. In this episode, Yuval sits down with Niv from AI21 to expose why most RAG evaluation is fundamentally flawed. From overhyped retrieval scores to chunking strategies that collapse under real-world complexity, they break down why your system isn’t as good as you think — and how structured RAG solves problems that traditional pipelines simply can’t. </p><p>Bonus: what do Seinfeld trivia, World Cup stats, and your enterprise SharePoint have in common? (hint: your RAG pipeline chokes on all of them).</p><p><strong>Key Topics:</strong></p><ol><li>Why most RAG benchmarks reward the wrong thing (and hide real failures)</li><li>The chunking trap: how bad segmentation sabotages good retrieval</li><li>When LLMs ace the answer—but your pipeline still fails</li><li>Structured RAG: pipeline that solves RAG problem over aggregative data (such as financial reports)</li><li>Evaluation tips, tricks, and traps for AI builders<p></p></li></ol><p><br></p>

<p>Building production AI systems is hard — especially when you’re pioneering entirely new categories. In this episode, Yuval speaks with Guy Becker, Group Product Manager at AI21, to trace the evolution from task-specific models to Agent planning and orchestration systems. Guy shares hard-won lessons from building some of the first RAG-as-a-service offerings when there were literally zero handbooks to follow.</p><p><strong>Key Topics:</strong></p><ol><li><strong>Task-specific models vs. general LLMs</strong>: Why focused, smaller models with pre and post-processing beat general purpose LLMs for business use cases.</li><li><strong>Building RAG before it was cool</strong>: Creating one of the first RAG-as-a-service platforms in early 2023 without any established patterns.</li><li><strong>The one-size-fits-all problem</strong>: Why chunking strategies, embedding models, and retrieval parameters need customization per use case.</li><li><strong>From SaaS to on-prem</strong>: Scaling deployment models for enterprise customers with sensitive data.</li><li><strong>When RAG breaks down</strong>: Multi-hop queries, metadata filtering, and why semantic search isn’t always enough.</li><li><strong>Multi-agent orchestration</strong>: How AI21 Maestro uses automated planning to break complex queries into parallelizable subtasks.</li><li><strong>Production lessons</strong>: Evaluation strategies, quality guarantees, and building explainable AI systems for enterprise..</li></ol>

<p>Everyone’s talking about AI agents, but most of what we call "agents" are just workflows in disguise. Real autonomous agents require planning. And that, changes everything. In this episode, Yuval speaks with AI21’s Algo Tech Lead, Nitzan Cohen about why the popular React framework isn’t enough and how planning architecture unlocks true agent capabilities.</p><p>Key Topics:<br>1. The difference between workflows/chains and real autonomous agents<br>2. Why React agents fail at complex tasks, parallel execution, and user transparency<br>3. Free text vs. code-based planning approaches and their trade-offs<br>4. How planning enables multi-agent systems and model delegation<br>5. Training planners with reinforcement learning and replanning mechanisms<br>6. Evaluation challenges: Gaia benchmark, Agent Bench, and building custom datasets<br>7. Practical advice: When to upgrade from React and which frameworks to use</p><p>From competitive analysis that runs in parallel to breaking down complex coding tasks, discover how planning transforms AI agents from simple tool-calling loops into sophisticated problem-solving systems.</p>

<p><strong>MCP (Model Context Protocol) is changing how developers connect AI applications to external tools – but what exactly is it, and why should you care?</strong> In this episode, Yuval speaks with Etan Grundstein, Technical Product Manager (and formerly Director of Engineering) at AI21, to break down the protocol that’s standardizing AI integrations, moving beyond basic weather APIs and calculators to real-world productivity workflows.</p><p><strong>Key Topics:<br></strong>1)<strong> </strong>What MCP actually is and how it differs from traditional tool calling<br>2) Real-world examples: Connecting AI to Jira, Notion, Git, and even Blender<br>3) The evolution from local MCP servers to cloud integrations<br>4) Authentication challenges and how they’re being addressed<br>5) Why developers are building MCP servers to build other MCP servers<br>6) Looking ahead: Agent-to-Agent protocols and what comes next</p>