We moved our production database from SQLite to PostgreSQL without slowing down
A 33-minute cutover window and 99 of 99 tables verified, shipped while the same codebase absorbed 637 merges and a dozen other initiatives.
For everyone
Insights
Notes from running the herd
Long-form thinking on coordinating AI coding agents, keeping their spend visible, and what becomes possible when the idea is the only bottleneck.
New here? Start with our guide to orchestrating AI coding agents →
Collide, forget, repeat: the three ways parallel agents get out of sync
Run enough clean-context coding agents in parallel and three problems appear: they collide, forget, and repeat house rules. Here's how CodeHerder fixes that.
For everyone
Optimise the file every agent reads before doing anything
Keeping CLAUDE.md small is best practice, but ours hit 231KB across 37 correct commits. Splitting it cut cost per turn 28%, turns per task by a third.
For everyone
Drive your herd from claude.ai and chatgpt.com
CodeHerder now speaks remote MCP: check tasks, triage the backlog, file a task, and comment, straight from claude.ai or chatgpt.com.
For everyone
The most expensive line in your agent config is the model name
Agent cost doesn't track codebase size. Swapping our judgment stage's reasoning model moved a story's cost 2.4x, and its lead time nearly 3x.
For everyone
Give your agents their own machine: what CPU contention costs a parallel herd
Parallel Claude Code sessions need dedicated hardware. Load-matched data puts one machine 40% ahead, and a spot m9g.xlarge holds ten sessions.
For everyone
Anatomy of an $8 feature: the itemised receipt for code no human wrote
944 user stories shipped in a week, with no human writing the code. Here's what the median one cost, and what each quality gate caught.
For everyone
10 things we learned running 100 billion tokens through a herd of AI agents
Two months of CodeHerder data: 1.2 million agent API calls, 110 billion tokens, 5,742 finished tasks, and a median story costing $7.54, done in 50 minutes.
For everyone
Shipping without code: a non-technical builder's playbook for AI coding agents
You don't need to write code to ship real software with AI agents. Brief clearly, review the right things, and let the gates do the work.
For product & leaders
Can you trust AI-generated code? A practical guide to reviewing agent work at scale
The real question isn't whether AI agents can write code. It's whether you can trust code you didn't watch get written. Here's how gates make that answer yes.
For everyone
How to run a team of AI coding agents: a practical guide to orchestration
Going from one AI coding agent to a coordinated herd that ships reviewed, cost-bounded work: the problems that show up, and the operating model that fixes them.
For everyone
Cost-aware AI engineering: keeping agent spend visible and bounded
Token spend is easy to lose track of with more than one agent running. Here's how to keep it visible per task, agent, and model.
For everyone
One agent is a tool; a herd needs a shepherd
A single coding agent is easy to supervise. Ten of them is a coordination problem nobody's tool was built to solve.
For everyone
Ship a product idea without an engineer
You know exactly what 'done' looks like. Here's how to go from a plain-language brief to a shipped, reviewed change, without writing a line of code yourself.
For product & leaders