Question: "Should I use an agent harness or a scaffold?" Answer: “Yes, you should.”

Is fine-tuning officially just hitting an API now? 🤔 For many people just building applications, maybe this is the way… Thinking Machines released Tinker, and it’s a compelling tool for fine-tuning open-source LLMs on their hosted infrastructure. It works really good too. We’re gonna check it out today. We’re gonna tinker. Come join us live: youtu.be/Mmo-B5HD0ac

Are you in control of your agent’s memory? We must tread carefully across sessions and longer-term interactions, but how? What should we persist, why, and when? These are the right questions to…keep in mind 🧠 Join us today to cover Agent Memory! Watch here: youtube.com/live/MYzuyEtKto4 #agents #memory #langgraph

🙋 How do GEPA optimizers, evals, and agents change prompt optimization? Or…do they? At all? ⚠️ Spoiler: GEPA is pretty dope, but beyond that maybe it’s just terminology rather than core concepts that we have to track the evolution of. Join us for our last live YouTube event of the year today as we deep dive into the state of prompt optimization, from agent harnesses to context optimization. What’s really new, and what should be in our toolkits as AI Engineers in 2026 beyond prompting? See you there: youtube.com/watch?v=x8qo_0SC…

⚒️ Introducing the LangSmith Agent Builder, a *real* agent builder, not just for building workflows. 🧑‍💻 Interesting, the entire no-code interface is completely different from previous Agent Builders, yet super familiar to everyone who uses LLMs! Join us live to check out the new tooling from @langchain , and to compare it the recent @OpenAI Agent Builder we covered in October. 🚀 We’ll build, ship, and share agents with both Agent Builders and talk about what’s going on under the hood of the LangSmith Agent Builder in the new and improved LangChain v1.0 ecosystem. Catch us live youtube.com/watch?v=Tj_8dKbt…

LangSmith Agent Builder by @langchain is now in Public Beta! 🚀 You can now build production-ready agents in < 5 minutes without writing a line of code - just chat with the builder. The twist: this isn't wrapper. Under the hood, it compiles using LangGraph's state machine and Deep Agents harness for true resilience. Stop prototyping. Start shipping. 🏗️🚢🚀 Join @GregOnLock & @llm_wizard for the breakdown. 👉 luma.com/adh3n7s3 #LangChain #AI #NoCode #DeepAgents

Want to know what it takes to build a state-of-the-art LLM from scratch in the US in 2025? @arcee_ai knows, and their CTO and Head of Research @latkins joins us today to walk us through the journey! See you at 1 PM, live! youtube.com/watch?v=hi8w8K1x… #pretraining #slms #OpenSource

We're stoked to chat more with @latkins this coming wednesday to talk about the Trinity family. RSVP luma.com/bq8258et

Happy Thanksgiving from the AI Makerspace community! We're grateful to our peer supporters, our community members, our students, and every person who contributes their ideas, questions and expertise. Keep building 🏗️ shipping 🚢 and sharing 🚀! #Thanksgiving

🧑‍💻LangChain is the “fastest way to build an AI agent” … for engineers. It’s the best OSS framework for agent orchestration. And now, v1.0 is out for the entire open-source LangChain ecosystem, which also includes LangGraph and LangSmith. This is a big moment for @langchain, and it signals the maturity of the AI Engineering industry heading into 2026 📈 Join us live today to check out the new release and to build, ship, and share some agents! Tune in! youtube.com/live/lSfAPNJx3xQ…

📈 How important is AI Engineering going to be in 2026? 🤖 Let’s cut through the noise to find out what’s really going on heading into 2026 with Agents, with AI transformations, across academia, government, and industry. 🧑‍💻 And of course, ask the ever-important question, “as a backend AI Engineer, what are the most important core concepts and code we need to know and understand?" Join @Dr. Greg and @The Wiz live today for a wide-ranging discussion on AI Makerspace’s take on the State of AI Engineering, 2025. See you there: luma.com/fnw1oc8y