liveBook · Manning

Agent gate

As explained in Vibe Engineering

An agent gate is a workflow control that invokes an AI agent to assess a proposed software change before it progresses through delivery.

An agent gate inserts AI review into delivery, but separates probabilistic advice from deterministic enforcement. Secret scanners and other reliable checks may block; models should normally warn. section 5.3.2

A disciplined agent gate follows these rules:

  • Run deterministic checks such as gitleaks before accepting a commit. section 5.3.2
  • Ask the model about questions linters cannot reliably answer, including error-handling philosophy, naming, conventions, and test coverage. section 5.3.2
  • Parse a structured verdict instead of grepping free-form output, and keep model findings advisory to avoid habituating developers to bypasses. section 5.3.2

How Vibe Engineering covers it

How deep it goes
Distinguishes blocking checks from advisory models and specifies structured output, but does not develop model evaluation or policy tuning.
Examples
Uses a gitleaks pre-commit hook, a structured Claude verdict, and a GitHub Actions pull-request reviewer.
What it assumes
Assumes familiarity with Git diffs, hooks, pull requests, shell commands, and automated checks.
What you can do after
Operate/configure Git hooks and GitHub Actions that enforce deterministic checks while presenting model findings as review feedback.
How it connects
Connects Git hooks, secret scanning, static analysis, code review, pull requests, and continuous delivery.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Vibe Engineering. The section links point to the parts of the book it draws on.