This episode cuts through the hype and gets to the core of what's actually valuable in building AI that works.
We're joined by Vivek Trivedy from LangChain, a leading voice on agent and harness engineering, and Geoffrey Huntley, the mastermind behind the Ralph Wiggum loop. We tackle everything from context engineering to the next level of harness engineering, and debate the skills you really need in this rapidly evolving field.
Tune in for practical insights and a healthy dose of skepticism as we explore the future of AI!
Check out our github: https://www.github.com/boundaryml/baml
AI That Works repo: https://github.com/ai-that-works/ai-that-works
Socials:
X: https://x.com/boundaryml
Discord: https://discord.com/invite/yzaTpQ3tdT
LinkedIn: https://www.linkedin.com/company/boundaryml/
⏱️ Chapters:
Intro
Agents: Basic Definition
Harness Engineering Defined
Introducing a New Concept
Throwing Compute at Problems
Surfing the Models
Infra and System Prompts
Building with Loops
Good Questions from Chat
Transcript
I've watched this one closely. Ask me anything about it and I'll point you to the exact moment.