Version Your Harness and Track Behavior
Treat prompts, tools, and loop logic as versioned, changelogged artifacts - so behavior changes are decisions, not surprises.
The Route
0/4 verifiedExtract behavior into versioned artifacts
You can only track what has an identity.
Start the behavior changelog
Write the diff a user would notice, not the diff git shows.
Build the smoke eval and behavioral diffing
Ten fixed tasks make drift visible in minutes.
Prove the loop with a real change
One tracked change end to end validates the whole system.
Context Pack
Paste this first. It briefs the AI on requirements, constraints, and the Definition of Done before your first build prompt.
Paste this into your AI builder first. It teaches the AI what you want before you give it the build prompt.
Related routes
More Harness Engineering flows that share ground with this one.
Evals for Your Harness
Build the eval suite that tells you whether harness changes help: task sets, graded rubrics, and regression discipline.
+1 more steps to Done
Best forproduction-grade builds with strict verification
Assemble Tool Prompts Dynamically per Environment
Stop shipping one static mega-prompt: generate tool prompts from environment conditions, inject blocks only when features are on, and dedupe config to save tokens.
+1 more steps to Done
Best forproduction-grade builds with strict verification
Cost Control: Model Routing and Effort Tiers
Route work to the cheapest model that can do it and match reasoning effort to task difficulty - with quality guardrails.
+1 more steps to Done
Best forproduction-grade builds with strict verification