The Tool I Built for Agents Explained My Own Code to Me
I built an onboarding tool for AI agents to understand unfamiliar repositories. Then I ran it on one of my own. The code had not changed. The structured reading did.
Read more →Blog
Building in public: insights on agentic collaboration, AI-human teamwork, and the tools we're creating.
When Code Moves Faster Than the Team
Code generation got cheap. Alignment did not. We think there's a benchmark category missing — one that measures whether project memory helps when the truth lives in prior team reasoning, not in the current codebase. Here's the category, the tasks, and early evidence from 27 tasks across 8 families.
Read more →Verification Beats Fluency: What Watercooler Prevents (A/B Test in Non‑Coding Planning)
Both teams produced good plans—until one question required verifying the past. The difference wasn't intelligence. It was whether the team could cheaply check institutional memory.
Read more →The Water Cooler Effect, Part 2: Architecture
Watercooler is a structured memory system for humans and agents, designed to preserve team context, reasoning, decisions, and critique over time.
Read more →The Water Cooler Effect, Part 1: Where It Started
A literal water cooler conversation changed how we think about creativity. Watercooler is our attempt to engineer that effect back into human–AI collaboration.
Read more →Making 'Why' Durable: Building a 2-Minute Watercooler Demo in Public
Watercooler has reached a baseline where it's useful, not just aspirational. We're starting a build-in-public series to produce a new 2-minute demo—and replace the one on our landing page.
Read more →