liveBook · Manning

PR feedback chat

As explained in "Looks Good to Me"

An interactive conversation about feedback on a pull request.

A PR feedback chat lets an author ask questions about AI-generated review comments in the context of the pull request. Instead of waiting for a reviewer to respond, the author can reply to a comment and request an explanation or more detail. section 13.3

A practical exchange

CodeRabbit comments on a changed line with a suggested improvement. The author replies to that comment, asks why the change is needed, and requests further details. Qodo provides a similar conversation through its /ask command on the pull request timeline. section 13.3

Use the conversation as a faster starting point, while keeping review decisions deliberate:

  • Ask the tool to explain a flagged issue or clarify the reasoning behind a suggested change. section 13.3
  • Treat the response as input rather than a verdict; AI can miss context and nuance or produce an invalid suggestion. section 13.3 section 13.6
  • Introduce the capability cautiously, because accuracy may be limited initially and can improve as the tool receives more team interactions. section 13.3 section 13.6
Figure 13.7 Chatting with CodeRabbit AI on a piece of PR feedback
figure

View an example of an author chatting with CodeRabbit about a specific piece of pull-request feedback. section 13.3

How "Looks Good to Me" covers it

How deep it goes
Explains comment-level questioning and adoption caveats, but stops short of prescribing a detailed conversation workflow.
Examples
Uses CodeRabbit comment replies, Qodo’s /ask command, and a figure showing a conversation about pull-request feedback.
What it assumes
Assumes familiarity with pull requests and code reviews while emphasizing that human reviewers retain final responsibility.
What you can do after
Apply it through CodeRabbit or Qodo to question AI feedback, then validate the response before changing or approving code.
How it connects
Connects pull requests with AI code review, human judgment, code review automation, and reviewer feedback.

This explainer was generated by Manning's knowledge graph from the text of "Looks Good to Me". The section links point to the parts of the book it draws on.