First-pass success rate
The share of tasks a coding agent completes in one run that pass checks and review without a person rewriting them; the main health metric of agentic delivery.
Agent output is cheap; rework is not. First-pass success rate counts how often an agent run ends in a change that is merged as it is, or with only small fixes. It moves with the quality of the input (a good PRP or spec), the validation loop and the codebase, so it measures the system around the agent more than the model.
It is usually tracked with a few related numbers: defect escape rate (bugs found after merge in agent-written changes), the share of changes merged without human edits, and cost per task. Put next to DORA metrics, they show whether agents speed up delivery or only move the work to review and fixing.
Related terms
- PRP (Product Requirement Prompt): A PRD rewritten for a coding agent: the goal and why, plus the exact files, patterns to follow and commands that prove the work is done.
- DORA metrics: Research-based measures of software delivery: how fast changes reach production and how often they fail.
- Software factory (AI agents): A pipeline where agents write and fix most of the code while people write specs, set guardrails, design the checks and decide what ships.
- Cost per task (agent unit economics): What one finished agent task really costs: tokens, retries, tool calls and the human time to review it, compared with doing it another way.
- Comprehension debt: The growing gap between how much code a system has and how much of it anyone on the team actually understands, a typical cost of fast AI-written code.
