Venture Crane

Field Notes from Running AI Agent Teams in Production

One studio, AI agent teams, real costs, honest failures. Most AI development content is vendor marketing or tutorials. This is what it actually looks like to ship products with agents.

New here? Start Here for curated reading paths, or read The System for the operating model behind it.

Articles

Deep dives on a single topic.

View all

What Happens When Your AI Agent Briefing Lies

Apr 9, 2026 · 6 min read

The session briefing said 10 alerts. There were 270. Fixing it took four tracks, $741 in compute, and a captain who refused to accept done.

Read article →

Agents Building UI They Have Never Seen

Mar 28, 2026 · 6 min read

Seventeen PRs, three editor panels, a navigation redesign, and 40 hours of agent time. The human directing the work has never opened the app in a browser.

Design Specs as Agent Infrastructure

Mar 28, 2026 · 7 min read

Agents building UI from text descriptions produce divergent implementations. Design specs loaded at startup solved this.

A Design Tool Bake-Off - Figma MCP vs Google Stitch

Mar 28, 2026 · 7 min read

We tested Figma MCP and Google Stitch head-to-head on the same three UI panels. Sixty API calls versus three.

Cross-Venture Context - Teaching Agents Where They Are

Mar 28, 2026 · 8 min read

Agents operating across multiple products need spatial awareness. Without it, they target wrong repos and leak secrets across contexts.

Ship Log

What changed this week.

View all
Apr 12, 2026

Killing the QA grading theatre

Mar 2, 2026

Wireframes and design specs in the agent workflow

Feb 25, 2026

Fleet Sprint Reliability Improvements

Feb 25, 2026

Writing app design sprint and editor panel

Feb 22, 2026

Giving the browser advisor live context access via remote MCP

Go Deeper