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. The agent workforce runs on Claude Code - Anthropic's CLI harness - with Claude as the foundation model.

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

Articles

Deep dives on a single topic.

View all

Our Grades Fell While the Code Got Better

Sep 13, 2026 · 7 min read

Five scored code reviews trended downward while each one triggered a real remediation wave. The score was measuring the reviewer, not the code.

Read article →

Sixty Notes Nobody Could Read

Sep 10, 2026 · 8 min read

An audit found 60 saved agent memories reachable from no index at all. The notes were fine. The delivery tier they were wired into was the defect.

Handing a Decision to a Human Needs a Real Acknowledgment

Sep 3, 2026 · 8 min read

An escalation ending in "reply with this code" is empty unless the code names a stable item and the reply names a verified person.

The Watchdog That Announced a Restart It Never Performed

Sep 2, 2026 · 9 min read

A supervision mechanism that logs its intent and then fails to act is worse than no supervision, because the log reads like recovery in progress.

The Alert That Cried Wolf Daily

Aug 23, 2026 · 6 min read

A reconciler that scans all history with no memory of what it already reported files the same finding every morning until nobody reads it.

Ship Log

What changed this week.

View all
Sep 14, 2026

The site: spam gate and scheduled publishing

Sep 12, 2026

September in review: the remediation wave

Sep 11, 2026

September in review: new pipeline, decommission, two more incidents

Aug 25, 2026

August in review: the latent-defect audit

Aug 24, 2026

August in review: six incidents

Go Deeper