Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Discovery] AI Bot reviewer triggering #3231

Closed
aj-codecov opened this issue Jan 15, 2025 · 2 comments
Closed

[Discovery] AI Bot reviewer triggering #3231

aj-codecov opened this issue Jan 15, 2025 · 2 comments

Comments

@aj-codecov
Copy link

Is your feature request related to a problem? Please describe.
“Engineers think that it’s not working because @-tting the bot doesn’t work like normal @-tting”

Describe the solution you'd like
Slash commands seem like the next most viable option, but this could also be solved by yaml or UI config of triggering the bot by default on every PR/every PR on a certain branch

Describe alternatives you've considered
See notion

@Adal3n3
Copy link

Adal3n3 commented Feb 3, 2025

2/3 meeting with @rohitvinnakota-codecov @suejung-sentry @RulaKhaled

  • The problem on this issue has been solved in [feat] Enable pagination for AI enabled repos  codecov-api#1101 @rohitvinnakota-codecov will release this solution today. Maybe we can improve the wording a bit as a next step. (say something like the bot has reviewed your pr... )
    Image
    This covers both scenarios for if the user makes some changes and the bot has no feedback, and if the user makes no changes and the bot has nothing to review.

  • "Can we set yaml config of triggering the bot by default on every PR/every PR?" @rohitvinnakota-codecov It's possible. It will be like the BA and coverage comments.

ToDO: Adalene follow up with @aj-codecov for other problem to solve.

@Adal3n3
Copy link

Adal3n3 commented Feb 6, 2025

@aj-codecov and I discussed on potential next steps. Concerns about automatically displaying AI-reviewer responses in every PR would be more user-friendly than typing "@codecov-ai-reviewer review," we're worried that the majority of AI responses currently aren't useful. Forcing users to read unhelpful AI responses could lead to frustration and potentially app uninstalls.

For example, if the AI bot automatically posts 4 unhelpful responses, developers might find them noisy and distracting, so we believe we should prioritize improving the quality and maturity of AI responses before implementing automatic posting.

Image

(cc @rohitvinnakota-codecov @suejung-sentry @RulaKhaled )

@Adal3n3 Adal3n3 closed this as completed Feb 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants