AI Engineer - Videos
Back to Channel
VoiceVision RAG - Integrating Visual Document Intelligence with Voice Response — Suman Debnath, AWS
In this workshop we will explore the integration of Colpali, a cutting-edge Vision based Retrieval Model, with voice synthesis for next-generation RAG systems. We'll demonstrate how Colpali's abili...
Government Agents: AI Agents Meet Tough Regulations — Mark Myshatyn, Los Alamos National Lab
Lightning talk given at the 2025 AI Engineer World's Fair. https://www.linkedin.com/in/markmyshatyn/
Future-Proof Coding Agents – Bill Chen & Brian Fioca, OpenAI
Coding agents are becoming one of the most active areas in applied AI, yet many teams keep rebuilding fragile infrastructure every time models or providers change. We believe there is a better way....
Katelyn Lesse – Evolving Claude APIs for Agents, Anthropic
Developers are building more and more complex, long-running, agentic systems. Learn how the Anthropic team is evolving the Claude Developer Platform to enable developers to get the best outcomes fr...
No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer
It seems pretty well-accepted that AI coding tools struggle with real production codebases. At AI Engineer 2025 in June, The Stanford study on AI's impact on developer productivity found: A lot of...
Defying Gravity - Kevin Hou, Google DeepMind
Why we built Google Antigravity, and discussing the future of agentic IDEs with Gemini 3. Speaker: https://x.com/kevinhou22 AIE is coming to London and SF! see dates and sign up to be notified of...
Building Cursor Composer – Lee Robinson, Cursor
Learn about the infrastructure, training, and evaluations used to build Cursor Composer, our first coding model. (https://cursor.com/blog/2-0) Speaker: https://x.com/leerob AIE is coming to Londo...
Music from AIE Code Summit - Instrumentals
By popular demand, we are releasing our music from the livestream + venue stage -- the instrumental tracks. Comment below if you want to see the vocal tracks released!
The Unbearable Lightness of Agent Optimization — Alberto Romero, Jointly
This talk introduces Meta-ACE, a learned meta-optimization framework that dynamically orchestrates multiple strategies (context evolution, adaptive compute, hierarchical verification, structured me...
Agents are Robots Too: What Self-Driving Taught Me About Building Agents — Jesse Hu, Abundant
In this talk, I break down the surprising parallels between robotics and agents: embodiment, statefulness, simulation, and more. The main lesson from self-driving: everyone thought perception was h...
Vision: Zero Bugs — Johann Schleier-Smith, Temporal
Software with zero bugs sounds absurd, or even impossible, in anything but simple situations, but it has been built. For example, NASA's Space Shuttle software achieved near-perfection (1 error per...
Compilers in the Age of LLMs — Yusuf Olokoba, Muna
Python is where ideas start—but it isn't where portable, low-latency software ends. In this talk, I'll show how we use LLMs inside a constrained, verifiable compiler pipeline to turn plain Python f...
Backlog.md: Terminal Kanban Board for Managing Tasks with AI Agents — Alex Gavrilescu, Funstage
Never leave your terminal to create and manage tasks for your AI agents. Backlog.md stores all your tasks as Markdown files in your Git repo. By exposing the main workflows and commands as MCP tool...
Infra that fixes itself, thanks to coding agents — Mahmoud Abdelwahab, Railway
This talk shows how we built Railway Autofix, a plug-in template you can drop into any Railway project to monitor your infrastructure, and open PRs with fixes when issues are detected. We use OpenC...
Context Platform Engineering to Reduce Token Anxiety — Val Bercovici, WEKA
Context Platform Engineering is the set of skills and tools to design, size, and configure systems optimized for Agent Swarm Context, at any scale. “KV-cache hit rate is the single most important ...
The Cure for the Vibe Coding Hangover — Corey J. Gallon, Rexmore
Download the slides, soundtrack and other resources from this talk at: https://vibecodinghangover.com Inspiration strikes! You fire up your favorite AI coding agent and tell it "Build me an app th...
Enterprise Deep Research: The Next Killer App for Enterprise AI — Ofer Mendelevitch, Vectara
Conversational AI has already proven itself as the first high-ROI enterprise AI application. But the real frontier lies beyond chat with high-value, document-centric workflows that still consume co...
Developing Taste in Coding Agents: Applied Meta Neuro-Symbolic RL — Ahmad Awais, CommandCode
Your coding agent writes code like an LLM bot. CommandCode writes code like me. Every developer has a coding agent now. What if your coding agent actually had taste? What if it understood not just...
What Data from 20m Pull Requests Reveal About AI Transformation — Nick Arcolano, Jellyfish
Engineering teams are spending millions on AI coding tools, but most have no idea what's actually working. Without hard data, you're flying blind – unable to tell which teams are actually using AI ...
Context Engineering: Connecting the Dots with Graphs — Stephen Chin, Neo4j
AI systems need more than intelligence; they need context. Without it, even the most advanced models can misinterpret information, lose track of details, or arrive at conclusions that don’t hold up...
From Stateless Nightmares to Durable Agents — Samuel Colvin, Pydantic
Building production AI agents reveals a harsh truth: stateless architectures that work for simple demos become impossibly painful at scale. When long-running workflows fail, you lose all compute, p...
AI Copilots for Tech Architecture: The Highest-ROI Use Case You’re Not Building — Boris B., Catio
AI copilots have already changed the game in software development. But the most strategic, highest-leverage use case is still overlooked: tech architecture decision-making. Architecture decisions d...
Hacking Subagents Into Codex CLI — Brian John, Betterup
Subagents are amazing tools for managing context, among other things. But Codex CLI doesn't have them. Let's change that! Brian John is a Principal Full Stack Engineer with over a decade of experi...
AI changes *Nothing* — Dax Raad, OpenCode
Everyone says AI changes everything. Dax Raad argues that when it comes to building a winning product, AI changes nothing. In this contrarian talk, Dax breaks down why the fundamental challenges o...
Z.ai GLM 4.6: What We Learned From 100 Million Open Source Downloads — Yuxuan Zhang, Z.ai
GLM 4.6 is the only open-source model currently tied for #1 on the LMSYS Chatbot Arena, standing shoulder-to-shoulder with GPT-4o and Claude 3.5 Sonnet. In this talk, Zhang Yuxuan from zAI breaks d...
AIE CODE Day 2: ft Google Deepmind, Anthropic, Cursor, Netflix, Cline, OpenAI, Meta, and METR
NOVEMBER 21 - all times in EST * 9:06 am – Opening Remarks Swyx | Organizer, AI Engineer * 9:11 am – Stop Building Agents Barry Zhang | AI Engineer, Anthropic Mahesh Murag | AI Engineer, An...
AIE CODE 2025: AI Leadership ft Anthropic, OpenAI, McKinsey, Bloomberg, Google Deepmind, and Tenex
Alex Lieberman – Co-founder, @MorningBrew & @tenex_labs – Your Leadership Track MC! Kath Korevec – Engineering, @GoogleLabs – Proactive Agents Katelyn Lesse – Head of Engineering, Claude Developer ...
AI Engineer Paris 2025 (Day 2)
Full schedule at https://www.ai.engineer/paris#schedule - Emil Eifrem, Co-Founder and CEO, Neo4j, “The State of^H^Hin AI Engineering” - Tushar Jain, President, Product & Engineering, Docker, “Demo...
Opening Keynotes - AIE Paris 2025 (Day 1)
The opening welcome reception is all about the hallway track and the expo -- meeting and mingling with other founders and engineers who are (mostly) based in Europe. However, for those who can't ma...
Rishabh Garg, Tesla Optimus — Challenges in High Performance Robotics Systems
A robot's behavior is influenced by the control policy, the software configuration, and electrical characteristics of the communication protocol. When unexpected behaviors arise, it is not straigh...
Building an Agentic Platform — Ben Kus, CTO Box
Explore the technical evolution of metadata extraction at Box and how it shaped the foundation of our AI platform. We’ll walk through our transition to an agentic-first design—why it was necessary,...
Five hard earned lessons about Evals — Ankur Goyal, Braintrust
The main thesis of the video is that building successful AI applications requires a sophisticated engineering approach that goes beyond simply writing good prompts. The speaker argues for the impor...
Perceptual Evaluations: Evals for Aesthetics — Diego Rodriguez, Krea.ai
Special session with KREA.ai's cofounder Diego Rodriguez on how evals for aesthetics and image/generative media work — the hardest kinds of evals. linkedin.com/in/asciidiego/ Timestamps 00:15 I...
How BlackRock Builds Custom Knowledge Apps at Scale — Vaibhav Page & Infant Vasanth, BlackRock
Investment Operations teams are the backbone of asset and investment management firms. Their day-to-day work not only enables portfolio managers to respond swiftly to market events but also ensures...
Form factors for your new AI coworkers — Craig Wattrus, Flatfile
Designing user experiences for AI means moving beyond traditional interfaces. Designers are grappling with how to create intuitive and effective interactions for these new AI capabilities, while g...
Fuzzing in the GenAI Era — Leonard Tang, Haize Labs
"Evaluation" is one of those concepts that every AI practitioner vaguely knows is important, but few practitioners truly understand. Is "eval" the dataset for measuring the quality of your AI syste...
Multi Agent AI and Network Knowledge Graphs for Change — Ola Mabadeje, Cisco
Traditional ticketing and testing workflows for change management and network operations often operate independently and lack critical real-world context and adaptive decision making capabilities. ...
Wisdom-Driven Knowledge Augmented Generation at Scale - Chin Keong Lam, Patho AI
The main thesis of the video is that by using a Wisdom-Driven Knowledge Graph, we can significantly enhance the quantitative analysis capabilities of Knowledge-Augmented Generation (KAG) systems. T...
The Next Unicorns: 7 Top AI startups from the HF0 Residency
HF0's Demo Days are usually hilariously oversubscribed and have never before been aired publicly. For the first time, they are joining the AIE stage to pitch AI Engineers. https://www.hf0.com/ Ti...
#define AI Engineer - Greg Brockman, OpenAI (ft. Jensen Huang)
Greg Brockman's career and advice for AI Engineers Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: htt...
The Future of Evals - Ankur Goyal, Braintrust
About Ankur Ankur Goyal is the founder & CEO of Braintrust—the developer platform that companies like Zapier, Notion, Instacart, Airtable, and more use to evaluate, log, and ship reliable AI produc...
Designing AI-Intensive Applications - swyx
Whether you call it a workflow or an agent, AI engineered applications are seeing user-input:LLM-call ratios go from 1:1 (ChatGPT) to 1:100 (Deep Research, Codex) and even 0:n (Ambient/Proactive ag...
How to look at your data — Jeff Huber (Chroma) + Jason Liu (567)
By the end of this talk, you'll understand what it takes to apply clustering techniques and data analysis to understand what is the valuable work that your AI application is doing through analyzing...
On Engineering AI Systems that Endure The Bitter Lesson - Omar Khattab, DSPy & Databricks
Will discuss the principles for building AI software that underpin DSPy, highlighting the differences between conventional prompting (or finetuning/RL) versus the design and programming of truly mo...
Evals Are Not Unit Tests — Ido Pesok, Vercel v0
How to think about evaluating a non-deterministic system — and how to actually succeed at it. About Ido Pesok Ido Pesok is an engineer and researcher at Vercel, working on the AI behind v0 and foc...
2025 is the Year of Evals! Just like 2024, and 2023, and … — John Dickerson, CEO Mozilla AI
AI is getting deployed without guardrails, without governance, without due diligence. Surely this is the year we’ll see a Fortune 500 CEO fired because of a preventable AI incident. Surely this i...
Vibe Coding with Confidence — Itamar Friedman, Qodo
Everyone wants to do Vibe Code, even large Enterprises. But how can we ensure that the generated code is well-grounded with the dev team's code and software development standards? In this talk, Ita...
AI Automation that actually works: $100M, messy data, zero surprises - Tanmai Gopal, Hasura/PromptQL
We will review the different kinds of automation use-cases, and the approach we used, that will drive over a $100M of expected annual impact by deploying AI for business critical initiatives. We w...
Full Workshop: Realtime Voice AI — Mark Backman, Daily
Voice AI agents today can conduct natural, human-like conversations and perform a wide variety of tasks: customer support, lead qualification, healthcare patient intake, market research, and more. ...
Vision AI in 2025 — Peter Robicheaux, Roboflow
Attendee-Only and Attendee-Led 10min lightning talks: see https://crowdcomms.com/aiengineer25/qanda/41445 Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming...