Episode 28: From Context Engineering to AI Agent Harnesses: The New Software Discipline

Episode notes

Lance Martin of LangChain joins High Signal to outline a new playbook for engineering in the AI era, where the ground is constantly shifting under the feet of builders. He explains how the exponential improvement of foundation models is forcing a complete rethink of how software is built, revealing why top products from Claude Code to Manus are in a constant state of re-architecture simply to keep up. We dig into why the old rules of ML engineering no longer apply, and how Rich Sutton's "bitter lesson" dictates that simple, adaptable systems are the only ones that will survive. The conversation provides a clear framework for leaders on the critical new disciplines of context engineering to manage cost and reliability, the architectural power of the "agent harness" to expand capabilities without adding complexity, and why the most effective evaluation of these new systems is shifting away from static benchmarks and towards a dynamic model of in-app user feedback.

Related episodes across the Index

Other episodes covering the same guests and topics, from across The B2B Podcast Index.

• The Real AI Advantage Isn't What You ThinkAI Proving Ground Podcast · on Data science91 / 100
• When AI Meets Legal feat. Eleanor Lightbody, CEO of LuminanceNext Gen Builders · on GenAI85 / 100
• Dose of Reality - Mark Hadfield and James James AddlestoneInspiring Futures · on Data science83 / 100
• Next-Gen Banking: How ABN AMRO is Rewriting the PlaybookFintech Files · on GenAI81 / 100
• What It Really Takes to Adopt Generative AI at ScaleData Analytics Chat · on GenAI81 / 100
• What happens to commerce and payments in a programmable world?Voice of MPE · on GenAI71 / 100

• Episode 41: The Verification Crisis: Why Trust Is the New Bottleneck in AI77 / 100
• Episode 40: The Economic Reality of AI: Friction, Talent, and the Future of the Firm97 / 100
• Episode 39: The 100-Year Lead: What Baseball Teaches Us About the Future of AI88 / 100
• Episode 38: Why AI Won’t Fix Your Data Culture, It Will Only Amplify It (And What To Do About It)83 / 100
• Episode 37: Engineered Intelligence and The Data Science Problem in AI86 / 100