BBitMonkey AI
Home / Case studies / T01
T01The Fourteen

Vishal Retail

Comparing AI systems for a business problem

Sign in to open this case study.

Sign in

The case

Vishal Retail handles 62,000 customer complaints a month in Nagpur. Each one has to be classified into one of eight categories, summarised, and routed to the right team. Three AI vendors have demonstrated; procurement has recommended the one with the lowest quote.

What is in it

  • 12 teaching steps, one animation each
  • 29 labs, checked live against the case data
  • 60 step questions, every option explained
  • 22 final paper questions, marked on submission
  • 12 Claude prompts, optional

The steps

  1. 162,000 complaints, three quotes · THE DECISION
  2. 2A demo is not evidence · THE DECISION
  3. 3Build the 20-case pack · THE TEST
  4. 4Gold labels and the rubric · THE TEST
  5. 5Run all three, score quality · THE TEST
  6. 6Where the errors sit · WHAT THE SCORES HIDE
  7. 7The metric that did not matter · WHAT THE SCORES HIDE
  8. 8Hallucination and review load · WHAT THE SCORES HIDE
  9. 9Privacy, residency, integration · THE FULL PICTURE
  10. 10Total cost of ownership · THE FULL PICTURE
  11. 11The weighted framework · THE FULL PICTURE
  12. 12Measured, claimed, and the pilot · THE FULL PICTURE