YouTube
6077 Cursussen
AI Engineering at Jane Street - Building Custom Coding Assistants for OCaml
Explore building custom AI coding assistants for OCaml at Jane Street, covering data collection, model training, evaluation, and seamless editor integration.
Scaling Agents for Gen AI Products
Discover how Bloomberg's AI Engineering head scales generative AI agents for financial products, covering infrastructure challenges and real-world implementation strategies.
Why Agent Engineering in 2025
Discover why Agent Engineering is the future focus for 2025 as swyx shares insights from the AI Engineer Summit on building autonomous AI systems and developer tooling strategies.
How Deep Research Works - Building Gemini's Personal Research Assistant
Discover how Google DeepMind built Gemini Deep Research to transform time-consuming research tasks into efficient AI-powered investigations across multiple domains.
Navigating AI's Frontier in 2025
Explore 10 hot takes on AI's technical future from Lux Capital's Grace Isford, covering agentic systems and LLM implications for human behavior in this NYC summit talk.
Rethinking How We Scaffold AI Agents
Discover how to build more robust AI agents by embracing computation over manual design, moving beyond traditional scaffolding to leverage the "bitter lesson" for scalable systems.
OpenAI for VPs of AI - Advice for Building Agents
Discover how OpenAI's Technical Success team accelerates enterprise AI adoption through proven frameworks, real case studies, and practical agent-building strategies for VPs and leaders.
Agent Evals - Finally, With The Map
Discover a systematic framework for AI agent evaluation beyond ad hoc metrics, building comprehensive quality assurance for reliable, effective, and safe agents.
Voice Agents - The Good, the Bad, and the Ugly
Discover the real challenges of building production-ready AI voice agents, from handling hallucinations to designing proper evaluation metrics and human handoffs.
Stop Guessing - Build Robust AI with Layered Chain-of-Thought
Discover how Layered Chain-of-Thought prompting and Multi-Agent Systems create transparent, self-correcting AI that verifies each reasoning step against knowledge bases for robust decision-making.
Your Evals Are Meaningless - And Here's How to Fix Them
Discover why most AI evaluation methods fail in practice and learn proven strategies to build meaningful evaluation systems that actually predict real-world AI agent performance.
Building Multi-Agent Systems with Finite State Machines
Discover how to build robust AI agents using state machines and the Actor model alongside LLMs for reliable, observable multi-agent systems with clear state management.