Quality scoring for the assistant's summaries

The scenario takes a transcript from sbermegamarket, AI summarizes it, and a check scores its completeness and accuracy, collecting the results in evaluation.

  • Summary quality in numbers
  • Completeness and accuracy scored
  • See what the assistant misses
  • Scores in one place
Webhook
Set it upScriptera

How it works

To connect sbermegamarket and Webhook, you don't need a developer: a ready-made scenario links them in minutes.

  1. Starts when: When fetching a dataset row
  2. Then: Download Transcript
  3. Then: Extract from File
  4. Then: Summarise Agent
  5. Then: Is Evaluating?
  6. Then: Evaluate Summarisation
  7. Then: Set Outputs
  8. Then: Set Metrics
  9. Then: OpenAI Chat Model
  10. Then: LLM
  11. Then: Output
  12. Starts when: Webhook
  13. Then: Get Gdrive URL

You can launch this sbermegamarket + Webhook integration in Scriptera: describe the task in plain words — the scenario is built, launched and monitored for you.

Similar scenarios