Organizations.

29 talks · 27 speakers

Accelerate your AI journey with Azure AI model catalog · Agentic Excellence: Mastering Evaluation of AI Agents with Azure AI Evaluation SDK

27 talks · 27 speakers

A year of Gemini progress + what comes next · Agentic Evaluations at Scale — For Everybody

23 talks · 26 speakers

Don't Build Agents, Build Skills Instead · Anthropic for VPs of AI

22 talks · 25 speakers

Agent Reinforcement Fine Tuning · Building Effective Voice Agents

17 talks · 11 speakers

Agentic GraphRAG: AI’s Logical Edge · Agentic GraphRAG: Simplifying Retrieval Across Structured & Unstructured Data — Zach Blumenfeld

15 talks · 15 speakers

Collaborating with Agents in Your Software Development Workflow - Jon Peck & Christopher Harrison, GitHub · Copilots Everywhere

14 talks · 10 speakers

Break It 'Til You Make It: Building the Self-Improving Stack for AI Agents · Build a Prompt Learning Loop

14 talks · 19 speakers

Compression at the Edge · #define AI Engineer

13 talks · 8 speakers

Does GenAI "belong" to data scientists? · Evals 101 — Doug Guthrie, Braintrust

10 talks · 8 speakers

Accelerating AI on Edge — Chintan Parikh and Weiyi Wang, Google DeepMind · Building Agent Interfaces: Lessons from Chrome DevTools (MCP) for Agents

9 talks · 5 speakers

Agents[REDACTED:location_address] Access[REDACTED:location_address] and the Future of Machine Identity · AI Pipelines and Agents in Pure TypeScript with Mastra.ai

7 talks · 6 speakers

Agents[REDACTED:location_address] Access[REDACTED:location_address] and the Future of Machine Identity · Building Agents (the hard parts!)

7 talks · 5 speakers

Full Workshop: Realtime Voice AI — Mark Backman, Daily · How to build the world's fastest voice bot

7 talks · 6 speakers

Compression at the Edge · How I automate my own job at Hugging Face using agents

6 talks · 3 speakers

Agent Output Is Not UX: Rendering Layer Your LLM Pipeline Is Missing - Bala Ramdoss, Amazon Lens · Building Blocks for LLM Systems & Products

6 talks · 6 speakers

7 Habits of Highly Effective Generative AI Evaluations · Data is Your Differentiator: Building Secure and Tailored AI Systems

6 talks · 7 speakers

AI Didn’t Kill the Web, It Moved in! — Olivier Leplus (AWS) & Yohan Lasorsa (Microsoft) · Building Agents at Cloud Scale — Antje Barth, AWS

6 talks · 5 speakers

Building Cursor Composer · Building your own software factory

6 talks · 5 speakers

AI Engineering Without Borders · Designing AI-Intensive Applications

6 talks · 5 speakers

AI System Design: From Idea to Production · Architecting Agent Memory: Principles, Patterns, and Best Practices

6 talks · 5 speakers

AI SDK v6 · Building durable Agents with Workflow DevKit & AI SDK

5 talks · 2 speakers

6 Things to Know about AIE World's Fair 2026 · Agents for Everything Else — swyx

5 talks · 5 speakers

Building Self-Coding Agents · Frontier Feud

5 talks · 6 speakers

Building Conversational AI Agents - Thor Schaeff, ElevenLabs · Give Your Chat Agent a Voice

5 talks · 2 speakers

12-Factor Agents: Patterns of reliable LLM applications · No Vibes Allowed: Solving Hard Problems in Complex Codebases

5 talks · 2 speakers

Building AI Agents that actually automate Knowledge Work · Effective agent design patterns in production

5 talks · 3 speakers

How fast are LLM inference engines anyway? · Taking Reinforcement Learning Cross Datacenter

5 talks · 2 speakers

Local Models: Trust, Control, Optimization · Modern Post-Training: A Deep Dive — Will Brown, Prime Intellect

5 talks · 4 speakers

Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It · Engineering voice agents: Latency, quality, and scale

5 talks · 3 speakers

Agents are built at the fringe: getting from 90 to 100 · Embeddings are Stunting Agents: How Codeium Breaks Through the Ceiling for Retrieval

4 talks · 4 speakers

Building Agents with Amazon Nova Act and MCP — Du’An Lightfoot and Banjo Obayomi · Ship it! Building Production-Ready Agents

4 talks · 3 speakers

Don't be data poor · Make your LLM app a Domain Expert: How to Build an LLM-Native Expert System

4 talks · 4 speakers

From model weights to API endpoint with TensorRT-LLM · Introduction to LLM serving with SGLang

4 talks · 3 speakers

Don't Build Slop (4 Levels of AI Agent Maturity) · Evals Are Broken, Use Them Anyway

4 talks · 2 speakers

Building Reliable Agentic Systems · How Forward Deployed Engineering is done at Factory

4 talks · 3 speakers

3 ingredients for building reliable enterprise agents · Architecting and Testing Controllable Agents

4 talks · 3 speakers

How to build world-class AI products — Sarah Sachs (Notion) and Carlos Esteban (Braintrust) · Notion's Token Town

4 talks · 1 speaker

From Stateless Nightmares to Durable Agents · Human seeded Evals — Samuel Colvin, Pydantic

4 talks · 2 speakers

The Last Human Code Review: Building Trust in AI-Generated Code · The State of AI Code Quality: Hype vs. Reality

4 talks · 4 speakers

Comprehend First, Code Later: The AI Skill I Rely On Daily · MCP Is Not Good Yet — David Cramer, Sentry

4 talks · 3 speakers

From Agent Traces to Agent Simulations — Rustem Feyzkhanov, Snorkel AI · Stop Making Models Bigger, Make Them Behave — Kobie Crawford, Snorkel

4 talks · 3 speakers

Building AI Agents with Real ROI in the Enterprise SDLC · The AI emperor has no DAUs: why most devs still don't use code AI

4 talks · 1 speaker

Compression at the Edge · Fixing bugs in Gemma, Llama & Phi-3

3 talks · 1 speaker

Full Walkthrough: Workflow for AI Coding — Matt Pocock · Building Great Agent Skills: The Missing Manual

3 talks · 3 speakers

Amazon AGI · From RL to IRL — Gaurav Mishra, Amazon AGI Lab

3 talks · 1 speaker

Frontier Feud · The 2025 AI Engineering Report — Barr Yaron, Amplify Partners

3 talks · 4 speakers

Bringing Continual Learning into Enterprises · Efficient Reinforcement Learning

3 talks · 2 speakers

From MCP to Scale: Pipelines That Build Themselves · The Rise of CaaS: Context-as-a-Service for Agentic AI

3 talks · 3 speakers

Building enterprise LLM agents that work · Building SOTA Open Weights Tool Use: The Command R Family

3 talks · 2 speakers

From Chaos to Choreography: Multi-Agent Orchestration Patterns That Actually Work — Sandipan Bhaumik · On Engineering AI Systems that Endure The Bitter Lesson

3 talks · 2 speakers

Agentic Search for Context Engineering · Information Retrieval from the Ground Up

3 talks · 2 speakers

Don't just slap on a chatbot: building AI that works before you ask · GTM Is You - Victoria Melnikova, Evil Martians

3 talks · 2 speakers

Hiring & Building an AI Engineering Team · The AI Pivot: With Chris White of Prefect & Bryan Bischof of Hex

3 talks · 3 speakers

Git push, get an AI API. · Hypermode Launch

3 talks · 3 speakers

Harnesses in AI: A Deep Dive · OpenRAG: An open-source stack for RAG — Phil Nash

3 talks · 4 speakers

How to Secure Agents using OAuth · It's 10pm. Do You Know Where Your Agents Are?

3 talks · 3 speakers

Building Deterministic Infrastructure for Non-Deterministic AI Agents · Production Evals For Agentic AI Systems

3 talks · 3 speakers

AI Agents for Performance: Ship Faster, Pay Less · The Infinite Software Crisis

3 talks · 1 speaker

How to Train Your Agent: Building Reliable Agents with RL · How we scaled 500m AI agents in production with 2 engineers

3 talks · 1 speaker

fun stories from building OpenRouter and where all this is going · The Next Unicorns: 7 Top AI startups from the HF0 Residency

3 talks · 2 speakers

Monetizing AI — Alvaro Morales, Orb · Revenue Engineering: How to Price (and Reprice) Your AI Product

3 talks · 1 speaker

How To Build an AI Strategy That Fails · How to construct domain-specific LLM evaluation systems.

3 talks · 5 speakers

AGI: The Path Forward · The Messy Reality of Scale: Synthetic Data and Pre-Training

3 talks · 3 speakers

Building AI Products That Actually Work · Designing Agents (The Floor Is the Frontier)

3 talks · 3 speakers

Lobster Trap: OpenClaw in Containers from Local to K8s and Back · Strategies for LLM Evals (GuideLLM, lm-eval-harness, OpenAI Evals Workshop) — Taylor Jordan Smith

3 talks · 3 speakers

How Transformers Finally Ate Vision · State of the Union: Why Local, Why Now

3 talks · 3 speakers

Rise of the AI Architect — Clay Bavor and Alessio Fanelli · The Agent Development Life Cycle

3 talks · 3 speakers

Can LLMs generate Enterprise Quality Code? — Prasenjit Sarkar, Sonar · Guide, Verify, Solve: The Engineering Discipline Agentic Development Demands

3 talks · 2 speakers

Combine Skills and MCP to Close the Context Gap · Skill Issue: How We Used AI to Make Agents Actually Good at Supabase

3 talks · 2 speakers

Building Durable, Production-Ready Agents with OpenAI SDK and Temporal · MCP Tasks (async)/ Why the heck aren't any agents supporting MCP tasks/async?

3 talks · 1 speaker

Building [REDACTED:username]: Gergely Orosz × Simon Eskildsen · Software Engineering + AI = ?

3 talks · 3 speakers

Build Your Own Deep Research Agent + Technical Writer · Context Engineering in 2026: Compaction, Memory & Cost

3 talks · 3 speakers

Building agents is trivial now, context is the next frontier · Mergeable by default: Building the context engine to save time and tokens

3 talks · 1 speaker

Enterprise Deep Research: The Next Killer App for Enterprise AI — Ofer Mendelevitch, Vectara · open-rag-eval: RAG Evaluation without "golden" answers.

3 talks · 2 speakers

Judging LLMs · Productionizing GenAI Models – Lessons from the world's best AI teams

3 talks · 4 speakers

How Zapier Builds AI Products and Features With the Help of Braintrust · Turning Fails into Features: Zapier’s Hard-Won Eval Lessons

3 talks · 3 speakers

Building an ACP-Compatible Agent Live — Bennet Fenner, Zed · CI in the Era of AI: From Unit Tests to Stochastic Evals

2 talks · 1 speaker

Build Systems, Not Code · Building an Autonomous Engineering Org

2 talks · 1 speaker

Conquering Agent Chaos · The Agent-Native Company

2 talks · 2 speakers

RAG Evaluation Is Broken! Here's Why (And How to Fix It) · Real AI Agents Need Planning, Not Just Prompting

2 talks · 1 speaker

Agents Need Receipts, Not More Tool Calls · Agents Need Receipts, Not More Tool Calls

2 talks · 2 speakers

DSPy: The End of Prompt Engineering · The Billable Hour is Dead; Long Live the Billable Hour?

2 talks · 2 speakers

Local Models: Trust, Control, Optimization · The Base Model is Dead

2 talks · 2 speakers

Data and Environment Curation for Post-training LLMs · OpenThoughts: Data Recipes for Reasoning Models

2 talks · 2 speakers

Agents reported thousands of bugs, how many were real? - Ian Butler and Nick Gregory · How to Improve your Vibe Coding — Ian Butler

2 talks · 2 speakers

Challenges to Scaling Agents for Generative AI Products · What We Learned Deploying AI within Bloomberg’s Engineering Organization

2 talks · 1 speaker

Bringing agents onto the world wide web · The Web Browser Is All You Need

2 talks · 2 speakers

Serving Voice AI at Scale — Arjun Desai (Cartesia) & Rohit Talluri (AWS) · State Space Models for Realtime Multimodal Intelligence

2 talks · 3 speakers

AI Copilots for Tech Architecture: The Highest-ROI Use Case You’re Not Building — Boris Bogatin and Toufic Boubez, Catio · Grounded Reasoning Systems for Cloud Architecture

2 talks · 3 speakers

Fast Models Need Slow Developers · From Mixture of Experts to Mixture of Agents … with Super Fast Inference

2 talks · 2 speakers

Evaling Video Slop · The Hierarchy of Needs for Training Dataset Development

2 talks · 2 speakers

How to look at your data; what to look for, how to measure · Retrieval Augmented Generation in the Wild

2 talks · 2 speakers

Devin 2.0 and the Future of SWE · The State of Model Routing — NVIDIA, Cognition, OpenRouter

2 talks · 1 speaker

Dark Factory: OpenClaw Ships Faster Than You Can Read the Diff · Malleable Evals: Why Are We Still Evaluating Adaptive Systems with Static Tests?

2 talks · 3 speakers

Forget RAG Pipelines—Build Production-Ready AI Agents in 15 Minutes · Specialized RAG Agents: Lessons learned from deploying complex AI systems in production

2 talks · 2 speakers

Building an AI assistant that makes phone calls · Convex Launch

2 talks · 3 speakers

Containing Agent Chaos · Ship Agents that Ship: A Hands-On Workshop for SWE Agent Builders

2 talks · 2 speakers

The Devops Engineer Who Never Sleeps · Why Your Agent Disagrees With Itself (And What To Do About It)

2 talks · 1 speaker

Build Your Own Deep Research Agent + Technical Writer · Turn 10,994 Notes Into Your Agents' Memory

2 talks · 2 speakers

Building & Scaling an AI Agent Swarm of low latency real time voice bots! · Giving a Voice to AI Agents

2 talks · 1 speaker

Agents Need Feature Flags · ReviewDebt: a practical framework for scoring every pull request — Sachin Gupta, eBay

2 talks · 2 speakers

Benchmarks Are Memes: How What We Measure Shapes AI—and Us · Dispatch from the Future: building an AI-native Company – Dan Shipper, Every, AI & I

2 talks · 1 speaker

Frontier AI at Home (literally) · State of the Union: Why Local, Why Now

2 talks · 1 speaker

How to Build Planning Agents Without Losing Control - Yogendra Miraje, FactSet · Skills are new features: Building Skill-Centric Harness — Yogendra Miraje, FactSet

2 talks · 2 speakers

The Next Unicorns: 7 Top AI startups from the HF0 Residency · WTF do people use Open Models for??

2 talks · 1 speaker

Customized, production ready inference with open source models: Dmytro (Dima) Dzhulgakov · Making Open Models 10x faster and better for Modern Application Innovation

2 talks · 1 speaker

Build Dynamic Products, and Stop the AI Sideshow · The Build-Operate Divide: Bridging Product Vision and AI Operational Reality

2 talks · 2 speakers

Proactive Agents · Your Coding Agent Just Got Cloned And Your Brain Isn't Ready

2 talks · 1 speaker

AI-powered entomology: Lessons from millions of AI code reviews · Don’t get one-shotted: Use AI to test, review, merge, and deploy code — Tomas Reimers, Graphite

2 talks · 2 speakers

Building efficient hybrid context query for LLM grounding · Hasura Launch: Realtime Data Connectivity for AI

2 talks · 2 speakers

How Building with AI Can Double the Throughput of Your Engineering Team · Shipping an Enterprise Voice AI Agent in 100 Days

2 talks · 2 speakers

How Intuit uses LLMs to explain taxes to millions of taxpayers · Why Off-the-Shelf AI Doesn't Understand Money

2 talks · 2 speakers

How Forward Deployed Engineering is done [REDACTED:username] Kepler · How Kepler Built Verifiable AI for Financial Services

2 talks · 1 speaker

Perceptual Evaluations: Evals for Aesthetics — Diego Rodriguez, Krea.ai · The Next Unicorns: 7 Top AI startups from the HF0 Residency

2 talks · 2 speakers

Infra behind Krea 2 - How to train and serve at scale · Training Krea 2 - What matters in generative model training.

2 talks · 1 speaker

Scaling Enterprise-Grade RAG Systems: Lessons from the Legal Frontier · The Hierarchy of Needs for Training Dataset Development

2 talks · 2 speakers

Building the platform for agent coordination · Taste & Craft: A Conversation with Tuomas Artman, CTO of Linear, and Gergely Orosz of The Pragmatic Engineer

2 talks · 3 speakers

360Brew: LLM-based Personalized Ranking and Recommendation — Hamed Firooz and Maziar Sanjabi, LinkedIn AI · Lessons from Building LinkedIn's GenAI Platform

2 talks · 1 speaker

Everything I Learned Training Frontier Small Models · Everything you need to know about Finetuning and Merging LLMs

2 talks · 2 speakers

Best Practices for Evaluating Large Language Model Applications with llmeval: Niklas Nielsen · What It Actually Takes to Deploy GenAI Applications to Enterprises

2 talks · 1 speaker

Agents vs Workflows: Why Not Both? · Every Harness Will Become A Claw

2 talks · 1 speaker

Long Tasks and Experienced Open Source Dev Productivity · Why Agent Hype can fall short of reality – Joel Becker, METR

2 talks · 2 speakers

GraphRAG methods to create optimized LLM context windows for Retrieval — Jonathan Larson, Microsoft · UX Design Principles for (Semi) Autonomous Multi-Agent Systems

2 talks · 1 speaker

Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It · Minimax M2

2 talks · 2 speakers

Decoding Mistral AI's Large Language Models · Why TTS Models Now Look Like LLMs — Samuel Humeau, Mistral

2 talks · 2 speakers

ALPHALAB: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs — Brendan Rappazzo · What RL Means for Agents

2 talks · 1 speaker

Agentic Enterprise: What Your CEO Must Know About AI · LLM Scientific Reasoning: How to Make AI Capable of Nobel Prize Discoveries

2 talks · 2 speakers

Simulation-Maxxing: How Nubank ships agents 20× faster with simulations · We Vetted 2,000 AI Skills Before They Reached Developers

2 talks · 1 speaker

Building AI Products That Actually Work · The New Lean Startup

2 talks · 1 speaker

State of the Union: Why Local, Why Now · The Desktop Frontier — Ahmad Osman, Osmantic

2 talks · 1 speaker

Paperclip: Open Source Human Control Plane for AI Labor — Dotta · What Does Done Even Mean? Agents and Paperclip's Liveness Model - Dotta, Paperclip

2 talks · 1 speaker

Building Metrics That Actually Work — David Karam, Pi Labs · Layering every technique in RAG, one query at a time

2 talks · 3 speakers

Medic for Apache Spark - First Aid for Failing Jobs - Drasko Profirovic, Pinterest · What We Learned from Using LLMs in Pinterest

2 talks · 2 speakers

LLM codegen fails and how to stop 'em · Self Driving Products: Product Signals to Pull Requests

2 talks · 2 speakers

The AI Pivot: With Chris White of Prefect & Bryan Bischof of Hex · Your MCP Server is Bad and You Should Feel Bad

2 talks · 1 speaker

Prompt Engineering Tactics · The Model Isn’t Wrong—You’re Just Bad at Prompting

2 talks · 2 speakers

How Forward Deployed Engineering is done at Ramp · Scaffold Wisely

2 talks · 2 speakers

Frontier Feud · RL for Autonomous Coding — Aakanksha Chowdhery, Reflection AI

2 talks · 2 speakers

Building AI For All · The 3 Pillars of Autonomy – Michele Catasta, Replit

2 talks · 2 speakers

The Cure for the Vibe Coding Hangover · The Dark Arts of Web Automation: Teaching Agents to Use Websites Like Humans

2 talks · 1 speaker

Agent Evals: Finally, With The Map · Will Agent Evaluation via MCP Stabilize Agent Networks?

2 talks · 1 speaker

GPU Cloud Deployment Without Leaving Your IDE — Audry Hsu, RunPod · Under 5 minutes to a deployed LLM endpoint — Audry Hsu, RunPod

2 talks · 2 speakers

BDD, ADR, PRD, WTF: Capturing Decisions for Humans and AI Alike — Michal Cichra, Safe Intelligence · Spec-Driven Testing for Agents With A Brain the Size of A Planet — Steven Willmott, Safe Intelligence

2 talks · 3 speakers

Build enterprise generative AI apps using Llama-3 at 1,000 tokens/s on the SambaNova AI platform · Llama 3 at 1[REDACTED:password]000 tok/s on the SambaNova AI Platform

2 talks · 1 speaker

Compute & System Design for Next Generation Frontier Models · The Geopolitics of AI Infrastructure

2 talks · 1 speaker

From Vibe Coding to Vibe Engineering · The End of Apps

2 talks · 3 speakers

Agentic Development Security · Through the AI Fog: The architectural decision the next 24 months of agentic security depends on.

2 talks · 2 speakers

2026: The Year the IDE Died · The emerging skillset of wielding coding agents

2 talks · 1 speaker

Does AI Actually Boost Developer Productivity? (Stanford / 100k Devs Study) · How to Quantify AI ROI in Software Engineering (Stanford Study / 120k Devs)

2 talks · 2 speakers

Building safe Payment Infrastructure for the autonomous economy · Mastering AI Pricing — Mayank Pant, Stripe

2 talks · 2 speakers

Events are the Wrong Abstraction for Your AI Agents · Vision: Zero Bugs

2 talks · 2 speakers

From Arc to Dia: Lessons learned in building AI Browser · Prototyping as Leadership: How a CTO Ships with AI Agents

2 talks · 2 speakers

From Copilot to Colleague: Building Trustworthy Productivity Agents for High-Stakes Work · Missing pieces of workflow automation

2 talks · 1 speaker

Agents on the Canvas in tldraw · tldraw computer

2 talks · 1 speaker

OpenLLMetry is all you need · Prompt Engineering is Dead

2 talks · 1 speaker

MCP Agent Fine-Tuning Workshop - Ronan McGovern · Text-to-Speech Data Preparation and Fine-tuning Workshop - Ronan McGovern

2 talks · 3 speakers

Cooking with fire without burning down the kitchen · The Robots Are Coming for Your Job, and That's Okay

2 talks · 4 speakers

Agentic SDLC at Uber - Building Blocks for Uber’s Software Factory · Building Closed-Loop Evals for a Multimodal Agent at Uber Scale

2 talks · 2 speakers

Beyond Static Intelligence: Evaluating Continual Learning · What We Learned From A Year of Building With LLMs

2 talks · 1 speaker

Anthropic's CCA Exam as a Field-Guide for Agentic Engineering · Why Agentic Systems Need Ontologies

2 talks · 2 speakers

How Juries and Librarians Can Solve GTM's AI Trust Problem · The Next Unicorns: 7 Top AI startups from the HF0 Residency

2 talks · 1 speaker

ChatGPT is poorly designed. So I fixed it · LLM Knowledge Bases: a practical guide

2 talks · 1 speaker

Benchmarking Coding Agents on New vs Legacy Codebases — Denys Linkov, Wisedocs · Structuring a modern AI team

2 talks · 2 speakers

Beyond Conversation: Why Documents Transform Natural Language into Code · Just do it. (let your tools think for themselves) - Robert Chandler

2 talks · 2 speakers

Building Trust in Enterprise AI: Evaluating Domain-Specific LLMs for Real-World Financial Scenarios · When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge

2 talks · 2 speakers

Every company should have a Brain — Garry Tan, Y Combinator · Imagination Engineering

2 talks · 2 speakers

Computer-use models will agentify the web, not APIs · The Bitter Layout or: How I Learned to Love the Model Picker

2 talks · 1 speaker

Memory Masterclass: Make Your AI Agents Remember What They Do! — Mark Bain, AIUS · Stop Using RAG as Memory

1 talk · 1 speaker

No more bad outputs with structured generation

1 talk · 1 speaker

Knowledge Graphs & GraphRAG: Techniques for Building Effective GenAI Applications

1 talk · 2 speakers

Building Alice’s Brain: an AI Sales Rep that Learns Like a Human - Sherwood & Satwik, 11x

1 talk · 1 speaker

Building Reliable Support Agents Using the Effect TypeScript Library - Michael Fester

1 talk · 1 speaker

The Coherence Trap: Why LLMs Feel Smart (But Aren’t Thinking)

1 talk · 1 speaker

Why Your AI UX Is Broken (and It's Not the Model's Fault)

1 talk · 1 speaker

From Ambient Documentation to Clinical Intelligence

1 talk · 1 speaker

Agents are Robots Too: What Self-Driving Taught Me About Building Agents — Jesse Hu, Abundant

1 talk · 1 speaker

SWE-Marathon: Evaluating Coding Agents at Billion-Token Scale - Rishi Desai, Abundant AI

1 talk · 2 speakers

Most Enterprise Agentic Projects Are Doomed — Here’s Why

1 talk · 1 speaker

Adaption Labs — Gradient-Free Continual Learning

1 talk · 1 speaker

Scaling Reinforcement Learning: Lessons from Trillion-Token Deployments at Fortune 500s

1 talk · 1 speaker

Climbing the Ladder of Abstraction

1 talk · 1 speaker

How to Run Evals at Scale: Thinking Beyond Accuracy or Similarity

1 talk · 1 speaker

Privacy First Enterprise AI: Building AI Agents that Never Leave Your Security Boundary

1 talk · 1 speaker

Judge the Judge: Building LLM Evaluators That Actually Work with GEPA — Mahmoud Mabrouk, Agenta AI

1 talk · 1 speaker

Covalent Launch: The GPU Cheatcode: Fine-tune 20 Llama Models in 5 Minutes

1 talk · 1 speaker

Building and evaluating AI Agents That Matter

1 talk · 1 speaker

Memory Masterclass: Make Your AI Agents Remember What They Do! — Mark Bain, AIUS

1 talk · 1 speaker

The Future of Qwen: A Generalist Agent Model

1 talk · 1 speaker

The Many Ends of Programming

1 talk · 1 speaker

Software Development Agents: What Works and What Doesn't

1 talk · 1 speaker

A Taxonomy for Next-Generation Reasoning Models

1 talk · 1 speaker

Shipping something to someone always wins

1 talk · 1 speaker

Automating Large-Scale Refactors with Parallel Agents

1 talk · 1 speaker

Trading Desks to Clinical Trials: Parallels in Applied Vertical AI

1 talk · 1 speaker

My AI Thinks I'm Eating My Feelings (and Other Nutritional Insights)

1 talk · 1 speaker

Why MCP and ChatGPT Apps Use Double Iframes — Frédéric Barthelet, Alpic

1 talk · 1 speaker

From Tokens to Cells: Foundation Models for Single-Cell Biology - Akram Baharlouei, Altos Labs

1 talk · 1 speaker

Useful General Intelligence

1 talk · 1 speaker

Harnessing the Power of LLMs Locally

1 talk · 1 speaker

Amp Code: Next-Generation AI Coding

1 talk · 1 speaker

One Registry to Rule them All - Sonny Merla, Mauro Luchetti, & Mattia Redaelli, Quantyca

1 talk · 1 speaker

Vending-Bench: Long-Horizon Agent Evals — Lukas Petersson, Andon Labs

1 talk · 1 speaker

Beyond the Harness: A Journey Towards Adaptive Engineering - Rajiv Chandegra, Annicha Labs

1 talk · 1 speaker

The rise of the agentic economy on the shoulders of MCP

1 talk · 1 speaker

Measuring AGI: Interactive Reasoning Benchmarks

1 talk · 1 speaker

How to defend your sites from AI bots

1 talk · 1 speaker

What Do Models Still Suck At?

1 talk · 1 speaker

The Adversarial Path to the Personal Assistant

1 talk · 1 speaker

How to Build Your Own AI Data Center in 2025

1 talk · 1 speaker

Training Frontier Models to Out-Think Hackers — Uri Rolls, Arithmetic & Thom Wolf, Hugging Face

1 talk · 1 speaker

How to Improve Your Agents: Academic Lit Review

1 talk · 1 speaker

Arrakis: How To Build An AI Sandbox From Scratch

1 talk · 2 speakers

Trends Across the AI Frontier

1 talk · 1 speaker

WTF Is the Context Layer? The Missing Infrastructure for Production Agents

1 talk · 1 speaker

Your Finance Agent's Bottleneck Is You

1 talk · 2 speakers

Securing Agents with Open Standards

1 talk · 3 speakers

The Future of Work

1 talk · 1 speaker

500 people vibe-coded for 30 days. I was one of them.

1 talk · 1 speaker

How to Kill the Code Review

1 talk · 1 speaker

Optimizing LLMs in Insurance with DSPy: Beyond Manual Tuning

1 talk · 1 speaker

Platforms for Humans and Machines: Engineering for the Age of Agents — Juan Herreros Elorza

1 talk · 1 speaker

Bending a Public MCP Server Without Breaking It — Nimrod Hauser, Baz

1 talk · 1 speaker

Unlocking Africa's Potential with AI — Thabang Ledwaba

1 talk · 1 speaker

Privacy-Preserving Intelligence — Steve Korshakov, Bee (acq. Amazon)

1 talk · 1 speaker

A2A & MCP: Automating Business Processes with LLMs

1 talk · 1 speaker

Building Multi-agent Systems with Finite State Machines

1 talk · 1 speaker

Full Workshop: Agent Auth Protocol — Paola Estefanía de Campos, Better Auth

1 talk · 1 speaker

Hacking Subagents Into Codex CLI — Brian John, BetterUp

1 talk · 1 speaker

Let’s Talk About FOMAT – Fear of Missing Agent Time

1 talk · 1 speaker

Black Forest Labs: FLUX, Open Research, and the Future of Visual AI

1 talk · 2 speakers

How BlackRock Builds Custom Knowledge Apps at Scale

1 talk · 1 speaker

Your AI Agent Isn't an Engineer: The Art of Thoughtful Anthropomorphism

1 talk · 1 speaker

Bolt.new: How we scaled $0-20m ARR in 60 days, with 15 people

1 talk · 1 speaker

Building AI Agents with Real ROI in the Enterprise SDLC

1 talk · 1 speaker

BotDojo Launch: Enhancing AI Assistants with Evaluations and Synthetic Data

1 talk · 1 speaker

fighting slop with slop

1 talk · 1 speaker

Building an Agentic Platform

1 talk · 1 speaker

Trust, but Verify: High-Fidelity Reasoning in Agentic Workflows

1 talk · 1 speaker

Teaching AI to Find Real Vulnerabilities — Prof. David Brumley, Bugcrowd

1 talk · 1 speaker

Scaling the Next Paradigm of Heterogeneous Intelligence

1 talk · 1 speaker

OpenClaw in Your Hand: Building a Physical AI Terminal for Local LLM Agents

1 talk · 1 speaker

Developer Experience in the Age of AI Coding Agents

1 talk · 1 speaker

How we hacked YC Spring 2025 batch’s AI agents

1 talk · 1 speaker

POC to PROD: Hard Lessons from 200+ Enterprise GenAI Deployments

1 talk · 1 speaker

Your coding agent doesn't always follow your rules

1 talk · 1 speaker

Ralph Loops: Build Dumb AI Loops That Ship

1 talk · 1 speaker

The Build-Operate Divide: Bridging Product Vision and AI Operational Reality

1 talk · 1 speaker

Build for the Memo, Not the Demo — Notes from 200 Investment Committees

1 talk · 1 speaker

Automating Escrow with USDC and AI

1 talk · 1 speaker

Multi-Agent AI and Network Knowledge Graphs for Change Management and Network Testing

1 talk · 1 speaker

General purpose robots as professional Chefs

1 talk · 1 speaker

The Unreasonable Effectiveness of Separating the Task from the Model

1 talk · 1 speaker

Move Fast Break Nothing

1 talk · 1 speaker

Memory Masterclass: Make Your AI Agents Remember What They Do! — Mark Bain, AIUS

1 talk · 1 speaker

The Making of Devin

1 talk · 1 speaker

How Forward Deployed Engineering is done at Cognition

1 talk · 2 speakers

ComfyUI Workshop with ComfyAnonymous and Jedrick Kosinski

1 talk · 1 speaker

Content Is Code

1 talk · 1 speaker

The Unofficial Guide to Apple’s Private Cloud Compute

1 talk · 1 speaker

State of Startups and AI 2025

1 talk · 1 speaker

The AI bugpocalypse is here. Now what?

1 talk · 2 speakers

AI is the World’s largest Relationship Therapist — Clay Cockrell & Tony Fabrikant, CoupleWork AI

1 talk · 1 speaker

From Self-driving to Autonomous Voice Agents — Brooke Hopkins, Coval

1 talk · 1 speaker

Using agents to build an agent company

1 talk · 1 speaker

Accelerating Mixture of Experts Training With Rail-Optimized InfiniBand Networking in Crusoe Cloud

1 talk · 1 speaker

The AI Pivot: With Chris White of Prefect & Bryan Bischof of Hex

1 talk · 3 speakers

Computer-Use 2.0: Agents Just Got Multi-Cursor

1 talk · 1 speaker

When Agents Meet Physical Data: The Other Physics of Agent Harnesses

1 talk · 1 speaker

DeepSWE: A Contamination-Resistant Coding Benchmark — James Shi, Datacurve

1 talk · 1 speaker

Small AI Teams with Huge Impact — Vik Paruchuri, Datalab

1 talk · 1 speaker

Skills are the New SDKs

1 talk · 1 speaker

Claude Fable, Claude Tag, and Anthropic's Culture — Cat Wu & Thariq Shihipar ft Simon Willison

1 talk · 1 speaker

Data Quality is the Compute Multiplier

1 talk · 1 speaker

The era of unbounded products: Designing for Multimodal I/O

1 talk · 1 speaker

AX is the only Experience that Matters

1 talk · 1 speaker

AI’s Jurassic Park Period

1 talk · 1 speaker

How Forward Deployed Engineering is done at Decagon

1 talk · 1 speaker

IT Admin for the AI Workforce — Sarthak Aggarwal, Decawork

1 talk · 1 speaker

Unveiling the latest Gemma model advancements

1 talk · 1 speaker

Let LLMs Wander: Engineering RL Environments — Stefano Fiorucci

1 talk · 1 speaker

What Breaks When You Build AI Under Sovereignty Constraints

1 talk · 1 speaker

Security Firewall for Agents

1 talk · 1 speaker

How to Hire AI Engineers When Everyone Is Cheating With AI

1 talk · 1 speaker

Iterating on LLM apps at scale: Learnings from Discord

1 talk · 1 speaker

Unlock Agent Autonomy: The Runtime for AI-Native Systems

1 talk · 1 speaker

The Unreasonable Effectiveness of Separating the Task from the Model

1 talk · 1 speaker

Build AI Systems for Discernment, Not Approval - Angel Ortmann Lee, Duolingo

1 talk · 1 speaker

Leadership in AI-Assisted Engineering

1 talk · 1 speaker

The State of MCP Observability: Observable.tools — Alex Volkov and Benjamin Eckel, Weights & Biases and Dylibso

1 talk · 1 speaker

How to add secure code interpreting in your AI app

1 talk · 2 speakers

The Friction Is Your Judgment

1 talk · 1 speaker

What It Actually Takes to Deploy GenAI Applications to Enterprises

1 talk · 1 speaker

Vibe Engineering Effect Apps

1 talk · 1 speaker

Emergence Launch: AI Agents and the future enterprise

1 talk · 2 speakers

Emulated: The data for fully autonomous software engineers and companies

1 talk · 1 speaker

Scaling Compute on Context

1 talk · 1 speaker

AI That Pays: Lessons from Revenue Cycle

1 talk · 1 speaker

No-code Fine-tuning: Mark Hennings

1 talk · 1 speaker

Letting AI Interface with Your App with MCP

1 talk · 1 speaker

MCP-UI: Extending the Frontier — Liad Yosef and Ido Salomon, MCP Apps

1 talk · 1 speaker

What if the harness mattered more than the model? - Aditya Bhargava, Etsy

1 talk · 1 speaker

The Era of Compound Engineering

1 talk · 1 speaker

Building a Smarter AI Agent with Neural RAG

1 talk · 1 speaker

EyeLevel Launch: Your RAG is Tripping, Here's the Real Reason Why

1 talk · 1 speaker

Making Codebases "Agent-Ready"

1 talk · 1 speaker

Code World Model: Building World Models for Computation

1 talk · 1 speaker

The State of Generative Media Today

1 talk · 1 speaker

Wearing the Agent: Engineering a Family-and-Friends Personal Agent, from Group Chats to Glasses

1 talk · 1 speaker

Chat and citations won't save your vertical AI

1 talk · 1 speaker

Making Open Models 10x faster and better for Modern Application Innovation

1 talk · 1 speaker

Building Reactive AI Apps

1 talk · 1 speaker

Form factors for your new AI coworkers

1 talk · 1 speaker

What the Best Agents Share

1 talk · 1 speaker

Let's integrate AI Agents in Event-Sourced Systems

1 talk · 1 speaker

Voice In, Visuals Out: The Agony and the Ecstasy

1 talk · 1 speaker

We Gave an Agent Production Code Access and Then Tried to Sleep at Night

1 talk · 1 speaker

State of the Union: Why Local, Why Now

1 talk · 1 speaker

Voice Agents: the good, the bad, and the ugly

1 talk · 1 speaker

To the moon! Navigating deep context in legacy code with Augment Agent

1 talk · 1 speaker

VoiceOps-fying Low-Latency Intelligence Extraction from Messy Audio Streams — Dippu Kumar Singh

1 talk · 1 speaker

Backlog.md: Terminal Kanban Board for Managing Tasks with AI Agents — Alex Gavrilescu, Funstage

1 talk · 1 speaker

Benchmarks: The Good, the Bad, and the Ugly

1 talk · 2 speakers

Serving Voice AI at $1/hr: Open-source, LoRAs, Latency, Load Balancing

1 talk · 1 speaker

Taming Rogue AI Agents with Observability-Driven Evaluation

1 talk · 1 speaker

Rethinking Team Building: How a 30-Person Startup Serves 50 Million Users — Grant Lee, Gamma

1 talk · 1 speaker

Agentic Security: Permissions, Provenance, and the Agent Supply Chain

1 talk · 1 speaker

Your Moat Is Your Data Model

1 talk · 1 speaker

The LLM Triangle: Engineering Principles for Robust AI Applications

1 talk · 2 speakers

Scaling to Long Horizons

1 talk · 1 speaker

How agents broke app-level infrastructure

1 talk · 1 speaker

AI Kernel Generation: What's Working, What's Not, What's Next

1 talk · 1 speaker

Building CISO-approved agent fleet architecture

1 talk · 1 speaker

How to build Enterprise-aware agents

1 talk · 1 speaker

The Next Unicorns: 7 Top AI startups from the HF0 Residency

1 talk · 1 speaker

A Practitioner's Guide to Graphs - Tim Ainge, Good Collective

1 talk · 1 speaker

Why you should care about AI interpretability

1 talk · 1 speaker

Teaching Gemini to Speak YouTube: Adapting LLMs for Video Recommendations to 2B+ DAU

1 talk · 2 speakers

How Evals and Prompts Shape Agent Behavior — Preetika Bhateja & Daniel Bump, YouTube Ads

1 talk · 1 speaker

Magic Editor Under the Hood: Weaving Generative AI into a Billion-User App

1 talk · 1 speaker

Training Albatross: An Expert Finance LLM

1 talk · 1 speaker

Neil Zeghidour - Voice AI: when is the "Her" moment?

1 talk · 1 speaker

Feedback Loops are All You Need

1 talk · 1 speaker

Code Generation and Maintenance at Scale

1 talk · 1 speaker

Breaking AI’s 1 Gigahertz Barrier

1 talk · 1 speaker

How to Build Trustworthy AI

1 talk · 1 speaker

How Coding Agents Change Software Development Forever - Hailong Zhang

1 talk · 1 speaker

Trust, but Verify

1 talk · 1 speaker

Building a 10-Person Unicorn

1 talk · 1 speaker

Fuzzing in the GenAI Era

1 talk · 2 speakers

The Current State of Browser Agents

1 talk · 1 speaker

Scaling Enterprise-Grade RAG Systems: Lessons from the Legal Frontier

1 talk · 2 speakers

Building Agentic Applications with Heroku Managed Inference and Agents — Julián Duque and Anush DSouza

1 talk · 1 speaker

Your AI Product Will Fail Unless You Can Explain It

1 talk · 1 speaker

HTML Is All Agents Need

1 talk · 1 speaker

Building security around ML

1 talk · 1 speaker

Research to Reality: Bringing frontier ML research to production

1 talk · 1 speaker

Guardrails First: Engineering Member-Facing Health AI

1 talk · 1 speaker

200 Million Patient Interactions Later: What the Generic Voice Stack Misses

1 talk · 1 speaker

Your Evals Are Meaningless (And Here’s How to Fix Them)

1 talk · 1 speaker

From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization

1 talk · 1 speaker

Invisible Users, Invisible Interfaces: Accelerating Design Iteration with AI Simulation

1 talk · 1 speaker

Real ROI: Lessons from Enterprises that Have already succeeded with LLMs [REDACTED:username] Scale

1 talk · 1 speaker

Everything is ugly, so go build something that isn't

1 talk · 1 speaker

Why We Don’t Need More Data Centers

1 talk · 1 speaker

Hyperspace: More Nodes Is All You Need

1 talk · 1 speaker

Build Your First Demand-Driven Context Base: Let AI Agents Tell You What They Need

1 talk · 1 speaker

Beyond the Prototype: Using AI to Write High-Quality Code

1 talk · 1 speaker

Lawrence Jones - Fighting AI with AI

1 talk · 1 speaker

Why your product needs an AI product manager, and why it should be you

1 talk · 1 speaker

State of Data

1 talk · 1 speaker

AI-Driven Multi-Document Correlation for Enterprise Financial Compliance and Fraud Detection

1 talk · 1 speaker

Your agent architecture has a half-life of 6 months

1 talk · 1 speaker

Persona Engineering: A Field Guide to AI Synthetic Personas — Ishan Anand, InsightSciences.ai

1 talk · 1 speaker

How Instacart transformed its search and discovery using an LLM-driven approach

1 talk · 1 speaker

Ionic Launch: Opening the economy to AI agents

1 talk · 1 speaker

Stop Writing Tone Instructions. Layer Them.

1 talk · 1 speaker

2026: The Year the IDE Died

1 talk · 2 speakers

Make your own event-sourced agent harness using stream processors

1 talk · 1 speaker

The AI Engineer’s Guide to Raising VC — Dani Grant (Jam), Chelcie Taylor (Notable Capital)

1 talk · 1 speaker

Building AI-Powered Developer Tools at Jane Street

1 talk · 1 speaker

Reverse Conway's law and GenAI: How agents will take over the organisation

1 talk · 1 speaker

What Data from 20 Million Pull Requests Reveal About AI Transformation

1 talk · 1 speaker

The Prompt Is Still a Punch Card

1 talk · 1 speaker

The Unbearable Lightness of Agent Optimization

1 talk · 1 speaker

Learned Execution Graphs for Anomaly Detection & Drift in APIs — Ritvik Pandya, JP Morgan Chase

1 talk · 1 speaker

Your Personal Open-Source Humanoid Robot for $8,999 — Jingxiang "JX" Mo, K-Scale Labs

1 talk · 1 speaker

Stop Renting Your Cognitive Infrastructure

1 talk · 1 speaker

Scaling AI in Education: A Khanmigo case study

1 talk · 1 speaker

Agentic Engineering: Working With AI, Not Just Using It — Brendan O'Leary

1 talk · 1 speaker

E-Values: Evaluating the Values of AI

1 talk · 1 speaker

I Run a Fleet of AI Agents Across Three Machines. Here's What Broke.

1 talk · 1 speaker

Why the Best AI Agents Are Built Without Frameworks (Primitives over Frameworks)

1 talk · 1 speaker

Developing Taste in Coding Agents: Applied Meta Neuro-Symbolic RL — Ahmad Awais, Command Code

1 talk · 1 speaker

Stop Burning Tokens: Why self-improvement needs domain expertise first - Annabell Schäfer, Langfuse

1 talk · 1 speaker

Skill issue: Lessons from skilling up coding agents to use Langfuse

1 talk · 1 speaker

Exposing Agents as MCP Servers with mcp-agent: Sarmad Qadri

1 talk · 1 speaker

Verifiable Environments for AI in Biology — Kenny Workman, LatchBio

1 talk · 1 speaker

AI Engineering 101

1 talk · 2 speakers

Everything Is a Rollout — Alex Shaw + Ryan Marten, Terminal-Bench, Harbor, Laude Institute

1 talk · 1 speaker

Your Fine-Tuned Model Is Tech Debt: A 50x ROI House of Cards

1 talk · 1 speaker

Agents need more than a chat

1 talk · 1 speaker

"I've never seen anything scarier than an LLM with tool calls." — Erik Meijer aka @HeadinTheBox

1 talk · 1 speaker

Voice agents with Realtime Video — Sidney Primas, LemonSlice

1 talk · 2 speakers

Your Insecure MCP Server Won't Survive Production — Tun Shwe, Lenses

1 talk · 1 speaker

On Curiosity — Sharif Shameem, Lexica

1 talk · 1 speaker

Your LLM Deception Monitor Is Broken. The Fix Is in the Training Data - Sachin Kumar, LexisNexis

1 talk · 1 speaker

The Age of the Agent

1 talk · 1 speaker

Why ChatGPT Keeps Interrupting You

1 talk · 1 speaker

Running Gemma 4 On-Device: 40 Tokens/s on iPhone with MLX

1 talk · 1 speaker

Government Agents: AI Agents Meet Tough Regulations — Mark Myshatyn, Los Alamos National Laboratory

1 talk · 1 speaker

How Lovable self-improves every hour

1 talk · 1 speaker

Dream Machine: Scaling to 1m users in 4 days — Keegan McCallum, Luma AI

1 talk · 1 speaker

Luminal - Search-Based Deep Learning Compilers - Joe Fioti

1 talk · 1 speaker

Beyond the Consensus: Navigating AI’s Frontier in 2025

1 talk · 2 speakers

Build Evals That Actually Matter - Nick Ung & Akshay Sharma, Lyft

1 talk · 1 speaker

Moondream: how does a tiny vision model slap so hard?

1 talk · 1 speaker

The Factory That Dreams: 39 AI Agents, No Framework

1 talk · 1 speaker

MCP Apps: Primitives, Discovery, and the Future of Software

1 talk · 1 speaker

Let's Build an Agent from Scratch — Kam Lasater

1 talk · 1 speaker

Building Intelligent Research Agents with Manus

1 talk · 1 speaker

Navigating Challenges and Technical Debt in LLMs Deployment

1 talk · 1 speaker

How to build an AI-Native Health Company

1 talk · 2 speakers

Moving away from Agile: What's Next?

1 talk · 2 speakers

MCP Apps: Extending the Frontier — Ido Salomon & Liad Yosef

1 talk · 1 speaker

What does it take to build a personal, local, private AI Agent that augments you deeply?

1 talk · 1 speaker

How we scaled 500m AI agents in production with 2 engineers

1 talk · 1 speaker

Second Order Effects

1 talk · 1 speaker

Stop Evaluating Models Like It's the 50s - Alejandro Vidal, Mindmakers

1 talk · 1 speaker

Decoding Mistral AI's Large Language Models

1 talk · 1 speaker

The Agentic Web and the Bazaar Era of AI - Ramesh Raskar, MIT Media Lab

1 talk · 2 speakers

How we taught agents to use good retrieval - Hanna Lichtenberg, Mixedbread AI

1 talk · 1 speaker

Unlocking Developer Productivity across CPU and GPU with MAX

1 talk · 1 speaker

From Systems of Record to Systems of Context

1 talk · 1 speaker

From Systems of Record to Systems of Context

1 talk · 1 speaker

RAG in 2025: State of the Art and the Road Forward

1 talk · 1 speaker

The infrastructure for the singularity

1 talk · 2 speakers

Llamafile: bringing AI to the masses with fast CPU inference

1 talk · 1 speaker

2025 is the Year of Evals! Just like 2024, and 2023, and …

1 talk · 1 speaker

Practical tactics to build reliable AI apps — Dmitry Kuchin, Multinear

1 talk · 1 speaker

Compilers in the Age of LLMs

1 talk · 2 speakers

The Agentic AI Engineer

1 talk · 1 speaker

Building Your Own Secure AI Workflows: Human-in-the-Loop Automation with n8n

1 talk · 1 speaker

CI/CD Is Dead, Agents Need Continuous Compute and Computers — Hugo Santos and Madison Faulkner

1 talk · 1 speaker

Agents Building Agents

1 talk · 1 speaker

SWE-rebench: Lessons from Evaluating Coding Agents on Real Software Engineering Tasks — Ibragim Badertdinov, Nebius

1 talk · 1 speaker

Intelligence + Continual Learning = Expertise

1 talk · 1 speaker

The Next Game Engine Won't Have a Manual

1 talk · 2 speakers

The Intelligent Interface

1 talk · 1 speaker

CI/CD Is Dead, Agents Need Continuous Compute and Computers — Hugo Santos and Madison Faulkner

1 talk · 1 speaker

Machines of Buying & Selling Grace

1 talk · 1 speaker

Stop Guessing: Build Robust AI with Layered CoT

1 talk · 1 speaker

HTML is All You Need (for Agents to Make Graphics)

1 talk · 1 speaker

Going beyond RAG: Extended Mind Transformers

1 talk · 1 speaker

Small Bets, Big Impact: Building GenBI at a Fortune 100

1 talk · 1 speaker

The AI Engineer’s Guide to Raising VC — Dani Grant (Jam), Chelcie Taylor (Notable Capital)

1 talk · 1 speaker

How to Leverage Domain Expertise — Chris Lovejoy, Notius Labs

1 talk · 1 speaker

A Genius With Amnesia

1 talk · 2 speakers

LLM Quality Optimization Bootcamp

1 talk · 1 speaker

Bypassing the Multimodal Tax: Framework-Free Hybrid RAG, Raw SQL RRF, and Live UI Telemetry

1 talk · 1 speaker

Bounded Autonomy: Between Free Will and Determinism

1 talk · 1 speaker

Compression at the Edge

1 talk · 1 speaker

The Log Is The Agent

1 talk · 1 speaker

The Missing Primitive for Agent Swarms

1 talk · 1 speaker

Healthcare’s Agent Bytecode: X12 as the Harness for AI Agents

1 talk · 1 speaker

The Next Unicorns: 7 Top AI startups from the HF0 Residency

1 talk · 1 speaker

I Gave an AI Agent the Keys to My Life (Here's What Happened)

1 talk · 1 speaker

Scaling Agents on Kubernetes with acpx and ACP

1 talk · 1 speaker

AI changes *Nothing* — Dax Raad, OpenCode

1 talk · 1 speaker

Agents in Production: How OpenGov Built and Scaled OG Assist

1 talk · 1 speaker

Recursive Coding Agents

1 talk · 1 speaker

When all context matters: Extended Cache Augmented Generation (ECAG)

1 talk · 1 speaker

Buy Now, Maybe Pay Later: Dealing with Prompt-Tax While Staying at the Frontier - Andrew Thompson

1 talk · 1 speaker

How Web Data Infrastructure Powers the Next Generation of AI

1 talk · 1 speaker

Self-Evolving Code with AI: Enhancing Quality and Security in CI

1 talk · 1 speaker

Wisdom-Driven Knowledge Augmented Generation at Scale

1 talk · 1 speaker

Personality-Driven Development: Exploring the Frontier of Agents with Attitude

1 talk · 1 speaker

Agents Don't Do Standups: Building the Post-Engineer Engineering Org

1 talk · 1 speaker

Anchoring Enterprise GenAI with Knowledge Graphs

1 talk · 2 speakers

Semantic Blindness: 500,000 Sensors Confused an LLM - Raahul Singh & Vanč Levstik, Phaidra

1 talk · 1 speaker

While my guitar gently speaks

1 talk · 2 speakers

Robotics: why now?

1 talk · 1 speaker

Building pi in a World of Slop

1 talk · 1 speaker

Foundry Local: Cutting-Edge AI Experiences on Device with ONNX Runtime and Olive — Emma Ning, Microsoft

1 talk · 1 speaker

Everything we knew about software has changed — Theo Browne

1 talk · 1 speaker

Maximize GPU Efficiency with Continuous Profiling for GPUs

1 talk · 1 speaker

Claws Out: Securing and Building with OpenClaw

1 talk · 1 speaker

From PM at Stripe to Building an AI Startup, a Recent Founder's Journey - Mounir Mouawad

1 talk · 1 speaker

Build the AI GTM Agent That Knows the Buyer Before the First Message

1 talk · 1 speaker

Beyond Components: Designing Generative UI for MCP Apps

1 talk · 1 speaker

LLM Safeguards: Security, Privacy, Compliance, Anti-Hallucination

1 talk · 1 speaker

Balancing Innovation with Security & Safety

1 talk · 1 speaker

Computer Use at the Edge of the Statistical Precipice

1 talk · 1 speaker

The UX of AI: Making AI-Powered Apps Your Users Don't Hate

1 talk · 1 speaker

The Agentic Web and the Bazaar Era of AI - Ramesh Raskar, MIT Media Lab

1 talk · 1 speaker

How Claude Code Works

1 talk · 1 speaker

"Data readiness" is a Myth: Reliable AI with an Agentic Semantic Layer — Anushrut Gupta, PromptQL

1 talk · 2 speakers

The 100-Tool Agent Is a Trap: Scaling with Semantic Routers and JIT Context

1 talk · 1 speaker

20 days of compute vs 7 hours: rethinking what state-of-the-art means — Bertrand Charpentier, Pruna AI

1 talk · 1 speaker

Analyzing 10,000 Sales Calls with AI in 2 Weeks

1 talk · 1 speaker

Beyond Transcription: Building Voice AI That Actually Understands Conversations

1 talk · 1 speaker

Navigating RAG Optimization with an Evaluation-Driven Compass

1 talk · 2 speakers

One Registry to Rule them All - Sonny Merla, Mauro Luchetti, & Mattia Redaelli, Quantyca

1 talk · 1 speaker

Navigating RAG Optimization with an Evaluation-Driven Compass

1 talk · 2 speakers

Evaluating AI Search: A Practical Framework for Augmented AI Systems

1 talk · 1 speaker

Autonomous Agents for Scientific Tasks - Sina Shahandeh, RADiCAIT

1 talk · 1 speaker

Infra that fixes itself, thanks to coding agents — Mahmoud Abdelwahab, Railway

1 talk · 1 speaker

How to Build AI Agents that Actually Work

1 talk · 1 speaker

A Song of Types and Agents

1 talk · 1 speaker

This video was edited with AI agent. But how?

1 talk · 1 speaker

Shift Left: How to Become an AI Engineer from a Full-Stack Background

1 talk · 1 speaker

The Next Medium: Why Real-Time Interactive Video Changes Everything — Ahmed Ahres, Reactor

1 talk · 1 speaker

How to construct domain-specific LLM evaluation systems.

1 talk · 1 speaker

Building an Agentic Video Editor for Mass Consumer

1 talk · 1 speaker

Velocity Sickness: What Happens When Your Whole Team Gets 10x Faster

1 talk · 1 speaker

Survive the AI Knife-Fight: Building Products That Win

1 talk · 1 speaker

Continual Learning for AI Agents: From Failures to Durable Improvements - Soheil Feizi, RELAI

1 talk · 1 speaker

Design like Karpathy is watching 😎

1 talk · 1 speaker

Always-on agents run production without the on-call tax

1 talk · 2 speakers

The Prompt is the Platform

1 talk · 1 speaker

The Miranda Hypothesis: How Hamilton (the Musical) Poisoned Your Persona Evals

1 talk · 1 speaker

How agents will unlock the $500B promise of AI

1 talk · 1 speaker

Can Oncology Workflows Run Without Human Touch? - Anant Shankhdhar, Risa Labs

1 talk · 2 speakers

Beyond APIs: How AI Web Agents Are Automating the "Long Tail" of Knowledge Work

1 talk · 1 speaker

Memory Harnesses for Long-Running Research Agents

1 talk · 1 speaker

A Practical Guide to Efficient AI

1 talk · 2 speakers

Llama 3 at 1[REDACTED:password]000 tok/s on the SambaNova AI Platform

1 talk · 1 speaker

You Didn't Ship a Bug. You Just Wrote It for a Human.

1 talk · 1 speaker

The Benchmarks Game: Why It's Rigged and How You Can (Really) Win

1 talk · 1 speaker

How to evaluate a model for your use case

1 talk · 1 speaker

Good design hasn’t changed with AI

1 talk · 1 speaker

Insights on Building AI teams

1 talk · 1 speaker

The Pipeline Is Dead

1 talk · 1 speaker

Are MCPs Overhyped? A Rant about MCPs

1 talk · 1 speaker

Develop at Idea Velocity

1 talk · 1 speaker

Breaking the Chain: Agent Continuations for Resumable AI Workflows

1 talk · 1 speaker

Insights from Snorkel AI running Azure AI Infrastructure

1 talk · 1 speaker

Simulation-Maxxing: How Nubank ships agents 20× faster with simulations

1 talk · 1 speaker

Announcing the AI Engineer Network

1 talk · 3 speakers

Evals Driven-Development: Engineering a Mental Health AI Coach Ethically & Safely

1 talk · 1 speaker

How To Build an AI Strategy That Fails

1 talk · 1 speaker

Personalization in the Era of LLMs

1 talk · 2 speakers

From Hype to Habit: How We’re Building an AI-First SaaS Company—While Still Shipping the Roadmap

1 talk · 1 speaker

The Future Is Domain-Specific Agents

1 talk · 1 speaker

User Signal Die at the Retrieval Boundary

1 talk · 1 speaker

Case Study + Deep Dive: Telemedicine Support Agents with LangGraph/MCP

1 talk · 1 speaker

Substrate Launch: the API for modular AI

1 talk · 1 speaker

GPU-less, Trust-less, Limit-less: Reimagining the Confidential AI Cloud

1 talk · 1 speaker

RLM: Recursive Language Models for Large Codebases

1 talk · 1 speaker

Multiplayer agentic engineering: enabling your whole team and your best agents to work together

1 talk · 1 speaker

Voice AI: Your Bot Isn't Special

1 talk · 1 speaker

AI Consulting in Practice — Nathaniel Whittemore (NLW), Superintelligent

1 talk · 1 speaker

The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked

1 talk · 1 speaker

When Will The Benchmaxxing Plague End?

1 talk · 1 speaker

Stateful environments for vertical agents — Josh Purtell, Synth Labs

1 talk · 1 speaker

What if the network was the sandbox?

1 talk · 2 speakers

Building a Chess Coach

1 talk · 1 speaker

Ending AI Slop

1 talk · 1 speaker

Evaluating AI Search: A Practical Framework for Augmented AI Systems

1 talk · 1 speaker

A Piece of PI – Embedding The OpenClaw Coding Agent In Your Product

1 talk · 1 speaker

Realtime Conversational Video with Pipecat and Tavus — Chad Bailey and Brian Johnson, Daily & Tavus

1 talk · 1 speaker

Shipping Products When You Don’t Know What they Can Do

1 talk · 2 speakers

Critical AI Inference Your CIO Can Trust

1 talk · 1 speaker

Paying Engineers like Salespeople

1 talk · 1 speaker

We Cut 94% of Our AI Coding Tokens With a Local Code Index. Here's the Architecture.

1 talk · 1 speaker

Enterprise Agents Have a Structure Problem - Ishita Daga, Tesla

1 talk · 1 speaker

Challenges in High Performance Robotics Systems

1 talk · 1 speaker

Context Is the New Code

1 talk · 2 speakers

Local Agentic Theory For Mobile Games — Shafik Quoraishee & Joanne Song, The New York Times

1 talk · 1 speaker

New York Times' Connections: A Case Study on NLP in Word Games

1 talk · 1 speaker

LLMs for the working programmer. Become a 10x programming centaur today!

1 talk · 1 speaker

Books reimagined: AI to create new experiences for things you know — Łukasz Gandecki, TheBrain.pro

1 talk · 1 speaker

Where AI is superhuman: The right jobs to automate with LLMs

1 talk · 1 speaker

Rethinking Environments for Long Horizon Work

1 talk · 1 speaker

Frontier Feud

1 talk · 1 speaker

The Demo I Wish I'd Had: OpenAI's Agents SDK... serverless!

1 talk · 1 speaker

AI Frontiers in Trust and Safety: Combatting Multifaceted Harm on Tinder at Scale

1 talk · 1 speaker

Running a Chess YouTube Channel Entirely by AI — Stephan Steinfurt, TNG Technology Consulting

1 talk · 1 speaker

E-Values: Evaluating the Values of AI

1 talk · 1 speaker

Build Your Own Deep Research Agent + Technical Writer

1 talk · 2 speakers

Shipping complex AI applications | Braintrust & Trainline

1 talk · 1 speaker

Scaling up Continual Learning

1 talk · 2 speakers

Production software keeps breaking, and it will only get worse. Here's how Traversal is fixing it.

1 talk · 1 speaker

Two Roads to Durable Agents: Replay vs. Snapshot — Eric Allam, Co-founder, Trigger.dev

1 talk · 1 speaker

Trunk Tools Launch: Disrupting the $15 Trillion Construction Industry with Autonomous Agents

1 talk · 1 speaker

Benchmarking semantic code retrieval on Claude Code

1 talk · 1 speaker

Designing AI to Scale Human Thought

1 talk · 1 speaker

Video Has No Memory. Here's How We Built One.

1 talk · 1 speaker

What's next after RLHF?

1 talk · 1 speaker

Shipping AI to a Million Patients Without an A/B Test

1 talk · 1 speaker

Advanced: Reinforcement Learning, Kernels, Reasoning, Quantization & Agents — Daniel Han

1 talk · 1 speaker

Active Graph Agent Runtime (BabyAGI 4)

1 talk · 1 speaker

Generative Video at the Speed of Light

1 talk · 1 speaker

AI tools for Forward Deployed Engineering

1 talk · 1 speaker

AI Agents, Meet Test Driven Development

1 talk · 1 speaker

Software Engineering Is Becoming Plan and Review

1 talk · 1 speaker

Viktor — AI Coworker That Lives in Slack

1 talk · 1 speaker

You Can't Prompt the Room: The Last Skill AI Won't Replace

1 talk · 1 speaker

The Z/L Continuum: Should AI Engineers Still Read Code?

1 talk · 1 speaker

The Missing Layer After Launch

1 talk · 1 speaker

GPT Web App Generator - 10,000 apps created in a month: Matija Sosic

1 talk · 1 speaker

Respect The Process

1 talk · 1 speaker

Waymo's EMMA: Teaching Cars to Think - Jyh-Jing Hwang, Waymo

1 talk · 1 speaker

Cognitive Exhaust Fumes, or: Read-Only AI Is Underrated — Šimon Podhajský, Head of AI, Waypoint

1 talk · 1 speaker

How Autoresearch Is Changing ML Research — Zhengyao Jiang, Weco AI

1 talk · 2 speakers

Context Platform Engineering to Reduce Token Anxiety — Val Bercovici and Callan Fox, WEKA

1 talk · 1 speaker

Knowledge Graphs in Litigation Agents — Tom Smoker, WhyHow.AI

1 talk · 1 speaker

Teaching Coding Agents to do Spreadsheets

1 talk · 1 speaker

Build Dynamic Products, and Stop the AI Sideshow

1 talk · 1 speaker

First Steps Toward Automated AI Research

1 talk · 1 speaker

Z.ai GLM-4.6: What We Learned From 100 Million Open Source Downloads — Yuxuan Zhang, Z.ai

1 talk · 1 speaker

Your Agents Need a Save Button

1 talk · 1 speaker

Citation Needed: Provenance for LLM-Built Knowledge Graphs

1 talk · 2 speakers

Which Jobs Can Be Replaced Today

1 talk · 2 speakers

Why We Killed Our Multi-Agent Pipeline — Subbiah Sethuraman and Abhilash Asokan, ZS Associates