> The current idea we have, how we could still benefit from having AI/Bot generated answers, is for maintainers and possibly triage teams to be able to review the proposed answers and "approve" them before they are posted. Such an answer might then be marked as "bot/automatically/AI generated" but it will also get a "Maintainer approved" or "Triage team approved" badge, This way anyone can see that the answer was reviewed by a maintainer/triage team member. This way we can get way more efficiency in handling issues (time for reviewing answers will be far less than writing it). Also maintainers/triage team members will be able to correct the answers if they are misleading / wrong. Who approved/corrected it will be visible for the triage/maintainer team in the DoSu interface, but not seen in the Github UI who actually approved/corrected it.
Love this! One thing we need to be a little sure of is the "honesty" while answering these bot suggestions, at least initially, so that the bot settles well into our ecosystem. I am happy with the direction this is heading into Thanks & Regards, Amogh Desai On Thu, Jun 27, 2024 at 1:31 PM Wei Lee <weilee...@gmail.com> wrote: > +1 for this idea. I remember we had this discussion during PyCon US, haha. > > So, in the first phase, we'll need a maintainer's approval before the AI > response is sent. I'm not sure whether this will be a burden to > maintainers. I'm thinking of adding a label to that AI response answer; the > user can decide whether to accept that even before the maintainers' > approval. If maintainers check the response and it's ok, they can remove > that label. > > Best, > Wei > > > On Jun 27, 2024, at 3:07 PM, Jarek Potiuk <ja...@potiuk.com> wrote: > > > >> > >> > >> I guess it's too early to discuss what the workflow we're picturing for > it > >> is. But I would like it if a reporter is unable to see the comment until > >> it's approved (which I guess is exactly what you're also suggesting > Jarek). > >> > > > > Absolutely. Actually - we (few of maintainers) can already see the > answers > > generated in a DoSU interface as "drafts" - and once we enable labelling > we > > can on-board more maintainers and triage team and work with DoSu team on > > implementing a workflow that might be good to start with. > > > --------------------------------------------------------------------- > To unsubscribe, e-mail: dev-unsubscr...@airflow.apache.org > For additional commands, e-mail: dev-h...@airflow.apache.org > >
