AI Engineer

I Gave an AI Agent the Keys to My Life (Here's What Happened) — Radek Sienkiewicz (@velvetshark-com)

Software Engineering Is Becoming Plan and Review — Louis Knight-Webb, Vibe Kanban

Mastering AI Pricing — Mayank Pant, Stripe

Agents on the Canvas in tldraw — Steve Ruiz, tldraw

Shipping complex AI applications — Braintrust & Trainline

Delivering reliable AI applications at scale requires moving beyond prototype-level development to robust operational workflows. This session outlines a systematic approach to industrializing generative AI, emphasizing the necessity of observability, structured evaluation, and continuous feedback loops. By breaking dow...

Agents for Everything Else — swyx

Building Conversational Agents — Thor Schaeff and Philipp Schmid, Google DeepMind

LLM codegen fails and how to stop 'em — Danilo Campos, PostHog

Replacing 12K LoC with a 200 LoC Skill — David Gomes, Cursor

OpenAI Codex Masterclass — Vaibhav Srivastav & Katia Gil Guzman

Codex functions as an advanced software engineering agent, capable of executing commands, running tests, and navigating complex codebases. The platform integrates with various surfaces like IDE extensions, CLI, and Slack, while leveraging unified agent harnesses for tool execution and safety. Key features include plugi...

Build & deploy AI-powered apps — Paige Bailey, Google DeepMind

Everything I Learned Training Frontier Small Models — Maxime Labonne, Liquid AI

Building your own software factory — Eric Zakariasson, Cursor

Why building eval platforms is hard — Phil Hetzel, Braintrust

One Login to Rule Them All: Cross-App Access for MCP — Garrett Galow, WorkOS

Gemma 4 Deep Dive — Cassidy Hardin, Researcher, Google DeepMind

Gemma 4 introduces a new family of open-source models featuring significant architectural advancements and expanded multimodal capabilities. The lineup includes two on-device models and two larger variants, notably the 26B mixture-of-experts (MOE) and the 31B dense model, both of which rank among the top open-source mo...

Scaling GitHub for your Agents — Sam Morrow, GitHub

Gateways are All You Need — Karan Sampath, Anthropic

The Model Context Protocol (MCP) presents significant operational hurdles for enterprises, specifically regarding observability, access control, and security. Implementing a gateway architecture serves as a critical middle layer that addresses these challenges by centralizing authentication, authorization, and credenti...

Collaborative AI Engineering: One Dev, Two Dozen Agents, Zero Alignment — Maggie Appleton, GitHub

Software development is fundamentally a team sport, yet current AI coding agents prioritize individual productivity, creating a "one-man, two-dozen agents" paradigm that ignores the necessity of collective alignment. As implementation becomes cheaper and faster, the primary bottleneck shifts from writing code to decidi...

MCP = Mega Context Problem - Matt Carey