AI Engineer - Videos
Back to Channel
Playground in Prod: Optimising Agents in Production Environments — Samuel Colvin, Pydantic
Deploying an agent is only the start. In this workshop, Samuel Colvin shows how to improve agents after they are already live, using Pydantic AI and Logfire to change prompts, models, and other par...
Vibe Engineering Effect Apps — Michael Arnaldi, Effectful
What if the best way to get coding agents to use a library well is not better prompts, but giving them the library's actual code? In this workshop, Michael Arnaldi walks through a practical approac...
Everything You Need To Know About Agent Observability — Danny Gollapalli and Ben Hylak, Raindrop
Agent failures do not look like normal software failures. In this workshop, the Raindrop team breaks down what it actually takes to monitor production agents, from explicit signals like tool errors...
Skills at Scale — Nick Nisi and Zack Proser, WorkOS
Chat interfaces are no longer limited to walls of text. In this talk, Liad Yosef and Ido Salomon explain how MCP Apps turn tools into interactive UI inside hosts like ChatGPT, Claude, VS Code, Curs...
The Multi-Agent Architecture That Actually Ships — Luke Alvoeiro, Factory
Everyone's building multi-agent systems, but nobody agrees on how. This talk proposes a taxonomy of five frontier multi-agent strategies and shows what happens when you compose them into a single a...
MCP UI: Extending the frontier — Liad Yosef and Ido Salomon, MCP Apps
Chat interfaces are no longer limited to walls of text. In this talk, Liad Yosef and Ido Salomon explain how MCP Apps turn tools into interactive UI inside hosts like ChatGPT, Claude, VS Code, Curs...
The Small Model Infrastructure Nobody Built (So We Did) — Filip Makraduli, Superlinked
Most embedding infrastructure assumes you know exactly which model you want ahead of time. This talk starts where that assumption breaks. Filip Makraduli walks through the real profiling mistakes, ...
Accelerating AI on Edge — Chintan Parikh and Weiyi Wang, Google DeepMind
As models get smaller and more capable, more AI workloads can move onto the device itself. In this talk, Chintan Parikh from Google DeepMind walks through what that looks like in practice, from Gem...
Demand-Driven Context: A Methodology for Coherent Knowledge Bases Through Agent Failure
Enterprise teams spend a lot of time trying to guess what AI agents need to know. This workshop flips that around. Instead of curating context top-down, Raj Navakoti shows how to build a demand-dri...
Training an LLM from Scratch, Locally — Angelos Perivolaropoulos, ElevenLabs
Training an LLM from scratch on a local machine sounds unreasonable, until it isn't. In this workshop, Angelos Perivolaropoulos from ElevenLabs walks through what it actually takes to train a langu...
Skill Issue: How We Used AI to Make Agents Actually Good at Supabase — Pedro Rodrigues, Supabase
Writing Agent Skills is easy. Writing ones that actually improve agent performance is not. In this hands-on workshop, you’ll build, test, and iterate on Agent Skills against real Supabase workflow...
Ralph Loops: Build Dumb AI Loops That Ship — Chris Parsons, Cherrypick
Dumb loops beat clever workflows. Most teams building with AI agents reach for multi-agent orchestration, planning graphs, and elaborate tool chains. Then they spend months debugging them. A single...
TLMs: Tiny LLMs and Agents on Edge Devices with LiteRT-LM — Cormac Brick, Google
Tiny LLMs are making on-device agents much more practical. In this workshop, Cormac Brick walks through how LiteRT-LM brings language models to edge devices, with a focus on Gemma, agent skills, an...
Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked
Agents can generate code. The hard part is generating code that's right for your system, team conventions, and past decisions. That's a context problem that naive RAG, MCP servers, and bigger conte...
Context Is the New Code — Patrick Debois, Tessl
As AI coding agents become more capable, context is starting to matter as much as code. Yet while code has version control, review, testing, CI/CD, and production observability, the prompts, rules,...
Human-in-the-Loop Automation with n8n — Liam McGarrigle
What does it actually take to build an AI workflow that can do useful work without becoming a black box? This workshop shows how to build secure, human-in-the-loop automations in n8n, using a Gmail...
I Gave an AI Agent the Keys to My Life (Here's What Happened) — Radek Sienkiewicz (@velvetshark-com)
An honest look at what happens when a personal AI agent is allowed to operate around the clock. Over months, one permission at a time, it went from reading files to handling email, backing up its o...
Software Engineering Is Becoming Plan and Review — Louis Knight-Webb, Vibe Kanban
AI eats the middle, software engineers are spending all their time planning and reviewing the work of AI. If all humans are going to do is plan and review the work of AI, the biggest lever you have...
Mastering AI Pricing: Flexible & Agile Monetization — Mayank Pant, Stripe
Monetizing AI is hard. Rising GPU and inference costs are squeezing margins, and traditional SaaS pricing simply does not work for the unpredictable compute demands of new-age AI companies. With mo...
Agents on the Canvas in tldraw — Steve Ruiz, tldraw
At tldraw, we've been bringing agents to our infinite canvas. In December 2025, we ran a one-month experiment named Fairydraw where users could work with three fairies—virtual collaborators who wor...
Shipping complex AI applications — Braintrust & Trainline
Getting a prototype working is straightforward. Making it reliable in production, especially with multi-step agents, tool use, and real users is the hard part. In this hands-on workshop, you'll wor...
Agents for Everything Else — swyx
How we run AI Engineer with Agents like Cognition's Devin and Town Assistant Speaker info: - x.com/swyx - github.com/swyxio
Building Conversational Agents — Thor Schaeff and Philipp Schmid, Google DeepMind
Thor Schaeff and Philipp Schmid show how to build conversational agents with Google DeepMind's Gemini APIs, from tool-using coding agents to realtime voice interfaces. The session covers the new In...
LLM codegen fails and how to stop 'em — Danilo Campos, PostHog
Danilo Campos breaks down the most common failure modes in LLM code generation and the practical strategies PostHog uses to prevent them. Drawing from a system that helps 5,000+ users each month, h...
Replacing 12K LoC with a 200 LoC Skill — David Gomes, Cursor
David Gomes shows how Cursor replaced a heavyweight WorkTrees feature with a lightweight layer built from skills, commands, and subagents. He walks through how parallel coding workflows were recrea...
OpenAI Codex Masterclass — Vaibhav Srivastav & Katia Gil Guzman
Codex is no longer just a coding assistant in a terminal. In this workshop, Vaibhav and Katia show how it becomes a full software engineering system, combining frontier models, the Codex app and CL...
Build & deploy AI-powered apps — Paige Bailey, Google DeepMind
Got a massive idea but stuck in the "just talking about it" phase? This session cuts the fluff and dives straight into how to build and prototype at lightning speed using AI Studio Build and Antigr...
Everything I Learned Training Frontier Small Models — Maxime Labonne, Liquid AI
A new class of small models is emerging with the ability to reliably follow instructions and call tools while running on-device under 1 GB of memory. In this talk, we'll break down how to post-trai...
Building your own software factory — Eric Zakariasson, Cursor
Most of us are pair-programming with one agent and stopping there. There's a lot more on the table. This workshop is about going from one agent to many. We'll start with codebase setup, the foundat...
Why building eval platforms is hard — Phil Hetzel, Braintrust
An eval platform is not just a test runner. You are building shared definitions of "good," reliable data pipelines, labelling workflows, versioning, and trust in results across many teams and model...
One Login to Rule Them All: Cross-App Access for MCP — Garrett Galow, WorkOS
Connecting a coding agent to multiple services often means facing a dozen OAuth consent screens, a dozen token lifecycles, and a dozen chances for something to break. Despite having Single Sign-On,...
Gemma 4 Deep Dive — Cassidy Hardin, Researcher, Google DeepMind
Open models are getting smaller, faster, and far more capable. In this talk, Cassidy Hardin walks through the latest advances in the Gemma family, with a focus on Gemma 4 and what it enables for de...
Scaling GitHub for your Agents — Sam Morrow, GitHub
GitHub operates one of the most heavily-utilised MCP servers in the ecosystem, with over 4 million downloads of the stdio server alone. Discover the architectural decisions, technical challenges an...
Gateways are All You Need — Karan Sampath, Anthropic
MCPs are often flaky, face multiple security vulnerabilities, and are generally hard to scale. Most enterprises struggle to use more than single digit numbers of MCPs due to issues with security, o...
Collaborative AI Engineering: One Dev, Two Dozen Agents, Zero Alignment — Maggie Appleton, GitHub
Agentic engineering so far has been a solo story: one developer and a dozen agents moving at warp speed. But speed without thoughtful planning and team alignment is just wasting tokens. When everyo...
MCP = Mega Context Problem - Matt Carey
The best MCP server is the one you didn't have to build. At Cloudflare we have a lot of products. Our REST OpenAPI spec is over 2.3 million tokens. When teams started building MCP servers, they di...
AgentCraft: Putting the Orc in Orchestration — Ido Salomon
As we run more agents in parallel, it becomes clear: we are the bottleneck. Luckily, the skills we need for effective multi-agent orchestration aren’t entirely new, they’ve just been hiding in unex...
Full Walkthrough: Workflow for AI Coding — Matt Pocock
A hands-on workshop covering the full lifecycle of AI-assisted development, from turning ambiguous requirements into agent-ready plans to running autonomous coding agents that ship production featu...
What Do Models Still Suck At? - Peter Gostev, Arena.ai, BullshitBench
What type of real world model responses do users still hate? We get to see millions of user's prompts - and we let users 'dislike both' on the Arena. We'll show you trends and examples of the tasks...
The End of Apps — Kitze, Sizzy.co
Speaker info: - https://x.com/thekitze - https://www.linkedin.com/in/kitaborovskis/
"Software Fundamentals Matter More Than Ever" — Matt Pocock
AI coding tools are overhyped and powerful at the same time. Used well, they're extraordinary. Used badly, they'll bury you in spaghetti code faster than any human team could. The difference isn't ...
Agents need more than a chat - Jacob Lauritzen, CTO Legora
Jacob Lauritzen is CTO at Legora, the fastest growing legal tech startup in history. Speaker info: - https://www.linkedin.com/in/jacob-lauritzen/ - https://github.com/Jacse
AIE Miami Day 2 ft. Cerebras, OpenCode, Cursor, Arize AI, and more!
April 21, 2026 - all times in EST -- 9:00am - Welcome to Day 2 -- 9:10am - David House, G2i Transforming Programming Mindsets: Case Studies in Agentic Coding Adoption -- 9:35am - Sarah Chieng, C...
Building Generative Image & Video models at Scale - Sander Dieleman, Google DeepMind
https://sander.ai/2025/04/15/latents.html Speaker info: - https://sander.ai/ - https://github.com/benanne - https://www.linkedin.com/in/sanderdieleman - https://x.com/sedielem Timestamps 0:00 Int...
How AI is changing Software Engineering: A Conversation with Gergely Orosz, @pragmaticengineer
Gergely Orosz is a formar Uber and Skyscanner engineer and is the author of https://www.engguidebook.com/ and https://www.pragmaticengineer.com/ , the #1 software/AI engineering newsletter on Subst...
Taste & Craft: A Conversation with Tuomas Artman, CTO Linear & Gergely Orosz, @pragmaticengineer
Tuomas Artman is Cofounder and CTO of Linear. - https://x.com/artman - https://www.linkedin.com/in/tuomasartman/ Timestamps 0:00 Introduction 0:36 The danger of shipping features too quickly with...
Running LLMs on your iPhone: 40 tok/s Gemma 4 with MLX — Adrien Grondin, Locally AI
See more: https://x.com/adrgrondin/status/2040512861953270226 Speaker info: - https://x.com/adrgrondin
AIE Miami Keynote & Talks ft. OpenCode. Google Deepmind, OpenAI, and more!
April 20, 2026 - all times in EST -- 9:00am - Welcome to AI Engineer Miami -- 9:10am - Gabe Greenberg, G2i Opening Remarks -- 9:15am - Dax Raad, OpenCode Keynote -- 9:40am - Dexter Horthy, Huma...
Full Workshop: Build Your Own Deep Research Agents - Louis-François Bouchard, Paul Iusztin, Samridhi
Deep research is one of the best ways to learn how to build real AI systems because it forces you to combine reasoning, planning, autonomy, tools, grounding, and feedback loops in a single end-to-e...
The New Application Layer - Malte Ubl, CTO Vercel
AI engineering is the legitimate successor to web development and the mainstream discipline that will define the next decade. Drawing on Vercel's own experience, Malte explores what it means to bui...