FB.
Series 8 parts

Engineering the Review Loop

Measure where delivery waits, bound AI review loops, gate merges on current evidence, and evaluate reviewers before ranking them.

Related: From code to merge: the illustrated Dev With AI talk guide.

A clockwise review cycle: measure waiting, rework and cost per accepted task; bound independent review by attempts and budget; gate the merge on current-revision evidence; improve tested controls and evaluate reviewers. Keep failed attempts in the accounting.

Measure the flow, bound review attempts, verify the current revision, then test improvements. This is the workflow to evaluate; the cycle does not establish an automatic learning system or a measured gain.

Open full-size infographic
  1. 1

    Coding faster moves the cost to verification

    AI can shorten implementation while specification, review, CI, and rework absorb the saved time. Instrument the full flow before adding more generation.

    Article ·
  2. 2

    When an independent reviewer earns its place

    Compare independent review with self-review and deterministic checks. Measure rescued defects, false acceptances, regressions and the cost of another pass.

    Article ·
  3. 3

    Designing a bounded review loop

    Build a bounded review loop with frozen inputs, separate execution and outcome fields, retry limits, evidence handoffs and human escalation.

    Guide ·
  4. 4

    A green review is not a merge gate

    A review signal matters only when its provider, commit SHA, coverage, execution state, publication, and place in branch policy are explicit.

    Article ·
  5. 5

    Turn recurring review comments into tested controls

    When the same accepted correction returns, test whether it belongs in a linter, type, test, example, repository rule, checklist, or architecture decision.

    Article ·
  6. 6

    Operating a multi-reviewer system safely

    Run local, CLI, and remote reviewers with explicit trust boundaries, least privilege, structured findings, budgets, degraded states, and shutdown controls.

    Guide ·
  7. 7

    5 AI code reviewers, 1 repository, and what developers did next

    Three months, 1,011 pull requests and 8,728 inline AI review comments: 4.5% got a visible human response. What the data shows, and what it cannot.

    Article ·
  8. 8

    Testing Opus 5.5 as the code-review baseline

    Opus 5.5 is the next reviewer baseline to test: set effort explicitly, update the API adapter, and keep a second reviewer only when it catches verified defects.

    Article ·