Skip to main content
Review

Get a code review that ranks issues by severity

Ask Gemini to review a diff for correctness, security, and clarity, rank findings by severity with a concrete failure scenario each, and skip style nits unless they hide a bug.

Il prompt

Review this change for correctness, security, and clarity. For each finding: give a severity (blocker / major / minor), the specific failure scenario, and the smallest fix. Skip pure style nits unless they hide a bug. If the change looks safe, say so plainly. Diff: [DIFF].

Sostituisci le variabili

[DIFF]

The diff or the changed files.

Quale modello usare

  • Gemini 3.1 ProSeverity judgement and failure scenarios need careful reasoning.

Input di esempio

  • [DIFF] = a pull request touching auth middleware.

Output di esempio

Pubblichiamo output di esempio solo da esecuzioni reali del modello. Questo template non è ancora stato testato formalmente, quindi non viene mostrato alcun output. Eseguilo tu stesso con l'input qui sopra.

Perché questa struttura funziona

  • Severity + failure scenario filters out noise and false alarms.
  • Permission to say "looks safe" reduces invented problems.

Errori comuni e soluzioni

Every line gets a comment.

Soluzione: Cap it: "Report at most the 5 most important findings."

Limiti noti

  • A model review complements, not replaces, human review and tests.

Non affiliato né approvato da Google. Gemini, Nano Banana e Veo sono marchi di Google LLC.