Skip to content
9 min readCritique

PR Review Agents vs Coding Agents: What Each One Should Do

Coding agents are built to change a repository. PR review agents are built to decide whether a change should be trusted. Mixing those jobs is how teams get noisy automation.

A coding agent changes code. A PR review agent judges code that changed. The distinction sounds small until the same model is asked to write a patch, defend the patch, review the patch, and decide whether it should merge. Good engineering workflows separate those roles.

The jobs are different

Agent responsibilities

Teams get better results when writing, reviewing, and fixing are treated as separate jobs with separate success criteria.

CapabilityCoding agentPR review agent
Primary goalProduce a requested change.Decide whether a proposed change is safe enough to merge.
InputPrompt, repository checkout, issue context, tests.PR diff, surrounding files, policy, historical context, review thread.
OutputCommits, patches, implementation notes.Findings, evidence, severity, verdict, suggested fixes.
Failure modePlausible but incomplete implementation.Noisy comments, missed blast radius, weak evidence.
Trust boundaryNeeds review before merge.Needs evidence before it can block merge.

Why one model is not enough

A single model can inspect a diff, but code review is not one skill. Security, test coverage, performance, API compatibility, data access, concurrency, and architecture all have different failure patterns. A useful review system has to route attention, not just produce prose.

This is why Critique uses a layered review shape: first map the change, then inspect specialist risk lanes, then synthesize a final human-readable verdict. The goal is not more comments. The goal is a smaller number of better claims, each with enough evidence for a maintainer to check quickly.

The right workflow

Weak loop
Prompt coding agentAccept patchSkim diffMerge under pressure
Stronger loop
Prompt coding agentOpen PRRun review agentFix findingsHuman approves

The stronger loop is especially important when AI generated the first draft. The fact that the code compiles does not prove that it respects the product contract, follows the surrounding architecture, preserves auth boundaries, or updates the tests that actually matter.

When to use each agent

Decision rules
  1. 1
    Do you need new code written?
    Use a coding agent. Give it a bounded issue, the relevant repository context, and a concrete verification command.
  2. 2
    Do you need a merge decision?
    Use a PR review agent. Give it the diff, policy, related files, and authority to produce an evidence-backed check result.
  3. 3
    Do you have a known narrow defect?
    Use a fix agent only after the finding is clear. Bounded repair works best when the problem is already localized and testable.
  4. 4
    Do you need to understand a codebase?
    Use repo chat or search first. Explanation work should not automatically become review work or patch work.

FAQ

It can provide a first-pass self-check, but it should not be the final reviewer. Independent review reduces confirmation bias and catches issues the implementation path made easy to overlook.
A useful PR review agent finds issues tied to the actual change, explains the affected path, assigns severity carefully, and avoids noisy comments that do not change the merge decision.
No. Some findings are architectural or product decisions. Automatic fixing is best for narrow, testable defects where the expected behavior is clear.
Critique reviews pull requests first. When a finding is narrow enough to repair, Remedy can attempt a bounded fix in an isolated environment and hand the result back with validation context.
Primary sources

Use the right agent for the right job

Run Critique where merge decisions already happen: on the GitHub pull request, with evidence, policy, and a clear verdict.

Install Critique

Ask about this essay

Nemotron-3-Super
Ask about the argument, the evidence, the structure, or how the post connects to Critique.
Not editorial advice · The essay above is the source of truth · Not saved to your account · OpenRouter privacy