BBitMonkey AI
Home / Case studies / P08
P08Applied Prediction and Automation

Expanded Package

Document-grounded knowledge assistant

Sign in to open this case study.

Sign in

The case

Setu General Insurance receives about 14,000 policy questions a month. Every answer is in the policy wordings and finding it takes an agent nine minutes. The assistant retrieves the relevant clause and either quotes it or refuses. The hard part is not answering - it is knowing when to refuse.

What is in it

  • 13 teaching steps, one animation each
  • 26 labs, checked live against the case data
  • 65 step questions, every option explained
  • 20 final paper questions, marked on submission

The steps

  1. 1Fourteen thousand questions a month
  2. 2What the assistant actually is
  3. 3What is in the documents, and what is not
  4. 4How often does it find the right clause?
  5. 5Clause or document?
  6. 6It always has an answer
  7. 7Two audiences, two systems
  8. 8The citation is the product
  9. 9Building the evaluation set
  10. 10Information, not advice
  11. 11When the wordings change
  12. 12Watching it once it is live
  13. 13The launch decision