Code owns severity
Fixed rules in code grade every alarm. The model writes the work order a person reads; it never decides how bad something is, because a model handed a verdict and asked to justify it fabricates the justification.
CLAUDE.md
Sweetwater Land & Cattle Co.
An agent loop that watches a simulated Wyoming cattle ranch while a simulator tries to break it. Five crews, one orchestrator, and a person who answers before anything on the ranch is changed.
Built by Scott Blodgett.
Recorded on 3 October 2026 with the previous models: a small model on our own computer, then Claude Opus 5. Sweetwater runs Claude Haiku 4.5 and Claude Opus 5.5 today.
Fixed rules in code grade every alarm. The model writes the work order a person reads; it never decides how bad something is, because a model handed a verdict and asked to justify it fabricates the justification.
CLAUDE.md
A model may propose a change to a ranch record and never makes one. The proposal waits at a LangGraph interrupt, checkpointed in Postgres so it survives a restart, until a person answers. Only then does the write go out, over MCP.
src/agent/gate.py
Code gathers each alarm's evidence into one page, so a model judges a page instead of driving a tool loop. Small models write well and navigate badly; that was measured twice before it became the rule.
CLAUDE.md
The one tool loop in the repo, LangGraph with langchain-mcp-adapters on a small local model, ran 28 times on thin pages and improved none of them. It is built, bounded and tested, and it ships off because the measurement said so.
docs/model-routing.md
The model key once expired and nobody knew for six weeks, because every failure path was quiet by design. Now a free check proves the key before any paid run, and a rejected key raises an alarm every round until it is fixed.
docs/cookbook.md
Four REST services and an MCP server with 19 tools, deployed elsewhere and frozen. The loop reads it every round and writes to it only after a person says yes. It never reads the ranch's source code: the contract is the wire.
One Python process, one round at a time, 11 steps: read the map, chaos, read sensors, count herd, apply rules, compare, assign crews, gather facts, AI crews, ask a person and report. The first 7 are plain code and cost nothing.
Claude Haiku 4.5 answers first and Claude Opus 5.5 takes over when the first answer is thin, both from one key. Postgres holds the alarms, the approvals waiting on a person, and every event these pages replay.
The repository is private while its history is cleaned for an open-source release.