Agentic Engineering

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

1. Define capability eval and regression eval.
2. Run baseline and capture failure signatures.
3. Execute implementation.
4. Re-run evals and compare deltas.

Task Decomposition

• each unit should be independently verifiable
• each unit should have a single dominant risk
• each unit should expose a clear done condition

Model Routing

• Haiku: classification, boilerplate transforms, narrow edits
• Sonnet: implementation and refactors
• Opus: architecture, root-cause analysis, multi-file invariants

Session Strategy

• Continue session for closely-coupled units.
• Start fresh session after major phase transitions.
• Compact after milestone completion, not during active debugging.

Review Focus for AI-Generated Code

• invariants and edge cases
• error boundaries
• security and auth assumptions
• hidden coupling and rollout risk

Cost Discipline

• model
• token estimate
• retries
• wall-clock time
• success/failure