How Evaluation-Driven Development (EDD) Works for AI Agents

What it is — A pre-merge evaluation gate for AI agent changes, using simulated inputs run through the real agent.

Key points

• An offline gate answering “does it work / did anything regress”.
• Simulate inputs (drawn from real traces), not outputs.
• Rejects always-on prod eval as too costly; runs targeted branch experiments with calibrated binary judges.