The panel

Specialist reviewers that stay in their lane.

General-purpose AI reviewers get noisy fast. PR Quorum gives you a catalog of specialists — three on by default, five more ready to enable, and fully custom reviewers you build yourself — each with its own model, focus list, confidence threshold, and posting behavior.

Specialist templates

On by default

Custom reviewers

Pro+

Model choice

any

Default reviewers

Correctness

Finds likely bugs, regressions, edge cases, and test gaps by arguing backward from runtime failure modes.

likely-bugregressionedge-casemissing-testnull-deref

Model

deepseek/deepseek-v4-pro

Best at

runtime bugs

Noise

balanced

Control

YAML

Security

Looks for secrets, auth bypasses, injection risks, unsafe data handling, and security-sensitive logic drift.

secret-leakauth-bypassinjectionunsafe-inputcrypto-misuse

Model

deepseek/deepseek-v4-pro

Best at

risk paths

Noise

strict

Control

YAML

Architecture

Keeps changes aligned with repository conventions, framework patterns, maintainability, and complexity budgets.

convention-driftover-abstractionpattern-violationcomplexity

Model

deepseek/deepseek-v4-pro

Best at

design drift

Noise

calm

Control

YAML

These are the default models. Route any reviewer to any OpenRouter model—using your key or ours—tune its focus and confidence, or add a custom specialist for each repository in .ai-review.yml.

More specialists, ready to enable

Enable these for any repository that needs them. The same noise controls still produce one focused review.

TestsEnable

missing test coverageflaky patternssnapshot driftmock misuse

PerformanceEnable

n+1 queriesunnecessary work in hot pathsmemory leaksbundle bloat

Frontend UXEnable

accessibilityloading and error statesunintended layout shiftmobile breakpoints

MigrationsEnable

destructive DDLunsafe defaultslong-running locksreversibility

AccessibilityEnable

ARIA correctnesskeyboard navigationcolor contrastsemantic HTML

Custom reviewers

Or build your own specialist

Create a reviewer with your own system prompt, focus list, and model — a house-style enforcer, a domain-rules checker, a flaky-test hunter. Up to 20 per panel. The default panel of three is free; enabling extra templates or custom reviewers requires Pro or above.

Start free on GitHub

Inside a reviewer

Prompts become typed findings, not vague prose

Each reviewer returns structured findings with severity, confidence, file, line, title, body, and an optional suggestion. That structure lets PR Quorum filter noise before it reaches the pull request.

1. System prompt

Reviewer focus list, merged with your .ai-review.yml policy

2. Pull request diff

Sent verbatim to OpenRouter chat completions

3. Structured output

Zod-validated JSON, parsed in the Inngest function

4. Confidence floor

Drop anything below min_confidence (default 0.75)

Example finding · structured output

{
  "severity":   "high",        // low | medium | high | critical
  "confidence": 0.87,          // 0..1, dropped below min_confidence
  "file":       "src/billing/stripe-webhooks.ts",
  "line":       142,
  "title":      "Webhook signature verified after side-effects",
  "body":       "...prose for humans...",
  "suggestion": "...diff-shaped fix..."   // optional, posted as GH suggestion
  // reviewerId is added by the runtime
}

Illustrative example — real findings reference your own code and diff lines.

Put the specialist panel on your next pull request

Start with the default three, enable five more from the catalog, or build your own—then tune the model, confidence, and focus for each repository.

Start free on GitHub Read the docs