Agentic Engineering

Engineering workflows where AI agents perform most implementation and humans enforce quality and risk controls.

When to Activate

• Setting up AI-assisted development workflows
• Planning agent task decomposition
• Optimizing model selection for cost/quality
• Reviewing AI-generated code

Operating Principles

1. Define completion criteria before execution
2. Decompose work into agent-sized units
3. Route model tiers by task complexity
4. Measure with evals and regression checks

Eval-First Loop