All episodes
The full archive of conversations exploring how AI is changing how we create, ship, and think about the work ahead.
Conversations in motion.
Watch, listen, build.
EP 7Give Coding Agents Eyes Beyond the Chat: Screen Recordings, Session History, and Devices
Your coding agent can inspect its chat, files, and terminal history, but it cannot see browser research, manual context transfer, distraction, or real device behavior. We show how screen recordings, session history, and device feeds can give agents that missing view.
EP 6Make Your Coding Agents Expert Designers
In this episode, we break down three real things we built: the Superlinear website, a custom minimap for our podcast editor, and a 3D game character. We show how breaking design into intermediate steps can give you better results and more places to steer.
EP 5Context Hygiene for Coding Agents: Murder, Lobotomy, or Diary
We break down how to keep coding-agent context clean: from clearing and compaction to side sessions, Pi, sub-agents, Beads, and other durable state layers.
EP 4Beyond Root-Level Harness Engineering: A Different Environment for Every Task
Task-specific harnesses can squeeze more intelligence out of coding agents. We explore how frontend, debugging, and performance environments can narrow context, enforce constraints, and better match the work.
EP 34 Emerging Practices in Agentic Engineering
Coding agents are becoming more capable, but getting better results increasingly depends on the systems, interfaces, and feedback loops we build around them.
EP 2Understanding Loops and Graphs in Modern Coding Agents
One prompt can become a hidden graph of sub-agents, each with its own context window and workstream. We unpack how agent harnesses grow from loops into graphs—and what that fan-out costs.