Review modes

Last updated: August 2026

Every review runs in one of three modes. Deeper modes read more context and cost more review units — your plan includes a monthly unit allowance (e.g. Pro includes 150).

How units are counted

Units are metered by how much work a review actually does, not by a flat per-review price. Reviewing a three-line fix is not the same amount of work as reviewing a 4,000-line refactor, and charging both the same would mean either overcharging small PRs or capping the quality of large ones.

Two numbers bound every review, so there are no surprises:

  • A floor — the mode’s listed minimum (Quick 0.5, Standard 1, Deep 2). Small pull requests always cost exactly this.
  • A ceiling — the most a single review can ever charge (Quick 10, Standard 20, Deep 40), no matter how large the pull request is.

Before you start a review, Pullora shows what comparable reviews of that repository have actually cost, along with your remaining balance. Afterwards, the exact figure appears in the review log and in the reviews list, so you can always see where your units went.

In practice most pull requests land at or near the floor. Units are only consumed by reviews that run — a review that fails is not charged, and a cancelled one releases its reservation back to your balance.

Quick — from 0.5 units

Checks: Only the changed diff, for the things that break production: obvious functional bugs, security issues, severe performance problems, data-loss risk, and breaking behavior.

Use it for: High PR volume, small changes, pre-merge sanity checks.

Standard — from 1 unit

Checks: Everything in Quick, plus maintainability, error handling, API misuse, missing edge cases and likely missing tests. Language-agnostic — it reviews whatever your PR changes, and applies framework-specific rules automatically where it recognises the stack.

Use it for: The default. Right for most day-to-day PRs.

Deep — from 2 units

Checks: Everything in Standard, plus related unchanged files as context — interfaces and types, call-sites, project config and rules — to catch architecture problems, backward-compatibility breaks, and contract implications.

Use it for: Risky changes: refactors, API/database contract changes, release branches.

How the default mode is chosen

Per repository, in order of precedence: a one-time choice when you submit a PR URL → dashboard repository settings → .ai-review.yml → your workspace default (Standard). Regardless of mode, findings pass the same validation pipeline — confidence gates, deduplication, and diff-line mapping — before anything is posted.