An AI-Native Dev Lifecycle Across R&D: The Plan

Описание и применение

<p><strong>TL;DR.</strong> AI coding agents now open pull requests faster than people can review them. Instead of reviewing faster, I plan to decide which PRs need a human at all. A PR review agent puts each PR in one of three risk tiers by written rules: merge on green, AI review with a human after merge, or human review before merge. It starts in <strong>dry run</strong>: people decide as today, and every disagreement is a finding. After merge, an alert-triage agent links alerts to recent merges and proposes reverts, never merging them. Part 2 will report what survived real PRs.</p> <p><em>T

Задача

<p><strong>TL;DR.</strong> AI coding agents now open pull requests faster than people can review them. Instead of reviewing faster, I plan to decide which PRs need a human at all. A PR review agent puts each PR in one of three risk tiers by written rules: merge on green, AI review with a human after merge, or human review before merge. It starts in <strong>dry run</strong>: people decide as today, and every disagreement is a finding. After merge, an alert-triage agent links alerts to recent merges and proposes reverts, never merging them. Part 2 will report what survived real PRs.</p> <p><em>T

Результат

<p><strong>TL;DR.</strong> AI coding agents now open pull requests faster than people can review them. Instead of reviewing faster, I plan to decide which PRs need a human at all. A PR review agent puts each PR in one of three risk tiers by written rules: merge on green, AI review with a human after merge, or human review before merge. It starts in <strong>dry run</strong>: people decide as today, and every disagreement is a finding. After merge, an alert-triage agent links alerts to recent merges and proposes reverts, never merging them. Part 2 will report what survived real PRs.</p> <p><em>T

Доказательства

An AI-Native Dev Lifecycle Across R&D: The Plan

Источник