Build 🏗️, Ship 🚢, and Share 🚀

Hey Practitioners, This is the last edition of the LLM Edge for 2025! We're off for our annual vacation from Christmas to New Year as a company 🎄🎆! But first, for our final YouTube event, we're covering DSPy tomorrow! In case you missed it, we covered LangSmith's chat-style Agent Builder and learned about Arcee's Trinity Models with their CTO over the past few weeks. Fresh off learning about one new open-model family of LLMs, The Wiz taught us about Nemotron 3 this week. As we prepare for...

LIVE TOMORROW! Trinity: A Family of Foundation Models Join us live tomorrow at 1:00 PM ET to hear about Trinity, the new family of foundation models from Arcee. They aim to reboot U.S. open source AI with this release! Join us live with CTO Lucas Atkins to dig into The Trinity Manifesto learn exactly how they trained their latest and greatest. IN CASE YOU MISSED IT! Agent Engineering LangChain hit v1.0, announced Series B, proclaimed Agent Engineering, and we were there to break down how...

LEARN SOMETHING NEW! Claude Agent Skills The hottest new skill in 2026? Skill Engineering. So meta. But what are agent skills? "Just README.md files with a little bit of YAML," but they make for some seriously next-level, on-the-fly context engineering. Although "Skills" are not yet an OSS capability across frameworks, we expect them to be. 🎥 Video 💻 Slides 🐙 Sample skills LIVE THIS WEEK! How to Build ChatGPT - Part V: Thinking & Deep Research Join us live tomorrow at 1:00 PM ET to learn how...

COMING UP! Claude Agent Skills Join us live today at 1:00 PM ET to break down Claude Agent Skills, which bring domain-specific expertise to general-purpose agents. Instead of relying on code or function calls, these “skills” use prompt expansion and context modification, letting Claude dynamically load only what’s needed to specialize for a task. It’s like giving your AI an onboarding guide, turning Claude into a fast, adaptable specialist for any domain. RSVP NOW! EVENT RECAPS Deep Agents,...

COMING UP! Agent Builder, by OpenAI Join us live tomorrow at 1:00 PM ET to break down AgentKit, the latest drop from OpenAI. Is Agent Builder really the low-code/no-code agent IDE we've all been waiting for? Tune in to find out, and to learn how it plays with other features in the new toolkit like Connector Registry, ChatKit, and Reinforcement Fine-Tuning! RSVP NOW! Build an End-to-End LLM Application, Live! Join us live tomorrow at 3:00 PM ET to learn how to build, ship, and share an...

COMING UP! Live from MLOps World/Generative AI Summit in Austin! Join us live from MLOps World/Gen AI Summit tomorrow afternoon! Join us to get in on the action, hear about what we learned from the keynote and morning talks on Wednesday, and what we're most excited for the rest of the week! If you're in Austin for the event, come see us at our booth in the Startup Zone! RSVP NOW! EVENT RECAPS Claude Agents SDK We've ascended to the meta zone! Claude Agent SDK - the rebranded Claude Code SDK -...

COMING UP THIS WEEK How to Build ChatGPT - Part III: Search & Agents SDK We're continuing our How to Build ChatGPT series this week with Agents! Join us live tomorrow to dive into a brief overview to understand exactly "What is an Agent?" and to learn how to build, ship, and share with the OpenAI Agents SDK RSVP now to Part III: Agentic Search & Agents SDK and Part IV: Vibe-Coding and Deployment 🏗️🚢🚀. REGISTER EVENT RECAPS How to Build ChatGPT I: Prompting & Responses API In our series...

COMING UP THIS WEEK How to Build ChatGPT - Part I: Prompting & Responses API We’re kicking off a new series: How to Build ChatGPT! 🚀 Step by step, we’ll cover everything from prompting and the Responses API to RAG, agents, reasoning, and full end-to-end application design—mirroring the journey that transformed ChatGPT from a simple front end into today’s powerful ecosystem. RSVP now to Part I: Prompting & Responses API and Part II: RAG and Connectors 🏗️🚢🚀. Part I: Prompting & Responses API...

COMING UP THIS WEEK Reinforcement Learning with Verifiable Rewards Join us for Reinforcement Learning with Verifiable Rewards. This new standard of RL is worth understanding today as an AI Engineer or LLM Engineering Practitioner. This session will get you up to speed on what makes RLVR different than previous methods we've studied before on our channel including RLHF, RLAIF, DPO, and others. We'll compare and contrast RLVR and GRPO (popularized by DeepSeek-R1) and build, ship, and share some...