Working Artifacts
Templates
Ready-to-use frameworks and structured documents for the practice of model behavior architecture. Each template is designed to be adapted, not just read.
Templates
specification
Model Behavior Specification
A structured template for defining what an AI system should and should not do — the foundational artifact of model behavior architecture.
design
AI Assistant Style Guide
A template for the voice, tone, and language patterns of an AI assistant — the design system for how the model talks.
design
System Prompt Architecture
A template and framework for structuring system prompts — the primary technical instrument for controlling AI behavior in deployed products.
design
Uncertainty Handling Guide
A template for how an AI system signals — and acts on — what it doesn't know.
evaluation
AI Product Behavior Audit
A template for systematically reviewing how an AI product behaves in production — what's working, what's broken, and what needs attention.
evaluation
Evaluation Rubric
A template for scoring model responses against defined behavioral criteria — the core instrument for systematic AI behavior testing.
evaluation
Failure Mode Report
A template for documenting a specific behavior failure — what happened, why, and what to do about it.
testing
Red-Team Test Set
A structured template for building adversarial test cases that probe the safety and robustness of AI behavior — covering jailbreaks, manipulation, edge cases, and policy boundary tests.
governance
Behavior Change Log
A template for tracking changes to model behavior over time — what changed, when, why, and what it affected.
governance
Escalation Policy
A template for deciding what an AI system handles on its own and what it hands off — to a human, a different system, or an emergency service.
governance
Refusal Policy
A template for documenting what an AI system refuses, why it refuses, and how it communicates refusals — making the hardest behavioral decisions explicit and consistent.
governance
Tool-Use Policy
A template for governing what tools an AI system can call, when it can call them, and what needs human confirmation.