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.
Lance on LinkedInContext Engineering for Agents by Lance MartinLearning the Bitter Lesson by Lance MartinContext Engineering in Manus by Lance MartinContext Rot: How Increasing Input Tokens Impacts LLM Performance by ChromaBuilding effective agents by Erik Schluntz and Barry Zhang at AnthropicEffective context engineering for AI agents by AnthropicHow we built our multi-agent research system by AnthropicMeasuring AI Ability to Complete Long Tasks by METRYour AI Product Needs Evals by Hamel HusainIntroducing Roast: Structured AI workflows made easy by ShopifyWatch the podcast episode on YouTubeDelphina's Newsletter