Skip to content

feat(automatedQA): integrate AI answer generation api DEV-739#6735

Merged
magicznyleszek merged 9 commits into
mainfrom
pamorim/dev-739-integrate-api-to-generate-with-ai
Feb 26, 2026
Merged

feat(automatedQA): integrate AI answer generation api DEV-739#6735
magicznyleszek merged 9 commits into
mainfrom
pamorim/dev-739-integrate-api-to-generate-with-ai

Conversation

@pauloamorimbr
Copy link
Copy Markdown
Contributor

@pauloamorimbr pauloamorimbr commented Feb 19, 2026

🗒️ Checklist

  1. run linter locally
  2. update developer docs (API, README, inline, etc.), if any
  3. for user-facing doc changes create a Zulip thread at #Support Docs Updates, if any
  4. draft PR with a title <type>(<scope>)<!>: <title> DEV-1234
  5. assign yourself, tag PR: at least Front end and/or Back end or workflow
  6. fill in the template below and delete template comments
  7. review thyself: read the diff and repro the preview as written
  8. open PR & confirm that CI passes & request reviewers, if needed
  9. delete this section before merging

📣 Summary

This PR implements the flow for activating the AI response generation feature and calling the actual generation endpoint

💭 Notes

  • For this to work some changes were necessary in the current TabAnalysis flow, so we could have access to the automated feature as well.
  • Now the manual_qual feature is created whenever a question is set and it's still not there. In the common flow it will happen once the first question is added. I chose that path instead of automatically creating the feature when TabAnalysis was opened, which i considered another viable option. This way we won´t create the feature unless the user really adds a qaQuestion.
  • There's a verification logic to decide whether to create the advanced feature for the AI generation, to patch it or do nothing if all qaQuestions are already set for it. This is important in the case of new questions being added.
  • Tags and Notes questions don't have Generate with AI enabled since it's not supported for them
  • The actual API call to generate the answer is working, but the generated data is not being parsed and displayed in this PR. We will take care of this in a follow up work.

👀 Preview steps

  1. ℹ️ have an account and a project with transcription
  2. have QA questions
  3. have autoQAEnabled feature flag enabled (?ff_autoQAEnabled=true)
  4. Press Generate with AI button in the analysis tab
  5. 🔴 [on main] notice that this won't trigger any action
  6. 🟢 [on PR] notice that this triggers activation of the feature for the existing questions and the API call for generating the answer with AI.

@magicznyleszek
Copy link
Copy Markdown
Member

@pauloamorimbr I tried testing it, but I get 500 error with AttributeError: &#39;Settings&#39; object has no attribute &#39;AWS_BEDROCK_REGION_NAME

Copy link
Copy Markdown
Member

@magicznyleszek magicznyleszek left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Generally works as described. Found two small things

@magicznyleszek magicznyleszek merged commit 2fe6451 into main Feb 26, 2026
11 checks passed
@magicznyleszek magicznyleszek deleted the pamorim/dev-739-integrate-api-to-generate-with-ai branch February 26, 2026 10:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants