Design

How I think about interfaces for AI, on both sides of an agent. Some are for people: the places where someone directs an agent, checks what it produced and corrects it. Others have the agent as their user: what it is given, and when. The pieces here describe one loop. What a person approves on one side is what the next agent should receive on the other. Each has something you can operate.

Reviewing what an agent wrote AI-human interface · Oct 2026 Four places a review of an agent's document goes wrong, and a prototype with an answer for each.

When knowledge reaches the agent AI-native interface · Oct 2026 One team rule and a ten-turn coding session: where each delivery route leaves the rule when the agent edits.