Case study · f. 02r

Study Material Assistant

An AI assistant trained on a student's own study material that shows exactly which page every answer came from.
Client
Bisma Ghani
Year
2026
Timeline
Working version in 3 days
Stack
Python, RAG, Citations, PDF parsing
  • First working version3 days
  • Answers without a sourceRefused
  • Source shownEvery answer

The problem

Generic chatbots answered confidently from the internet, not from the course. For exam prep that's worse than useless: a wrong answer that sounds right.

The client needed to trust the assistant, which meant seeing where each answer came from and being able to check it.

The approach

  1. 01

    Scope first, in plain English

    Before writing code we agreed on what "correct" meant: answer only from the uploaded material and show the source, otherwise say "not in your notes".

  2. 02

    Citations as a feature, not a footnote

    Every answer links back to the exact document and page, so the student can open the original and verify it in seconds.

  3. 03

    Flagging risk early

    One requested feature would have mixed outside knowledge into answers and quietly broken accuracy. We flagged it on day one and designed around it instead.

The outcome

A working version was delivered in three days. Answers the material can't support are declined, not invented.

Delivered a working version in 3 days. He flagged risks early, explained technical trade-offs in plain English, and even told me when one of my ideas would break the accuracy. He was right. Exactly what you want in an AI developer.

Bisma Ghani · Client
Next case · f. 03rHealthMate1 upload to a readable summary

Colophon · Your move

Ask me anything.
I'll cite my sources.

Karachi · UTC+5Overlap with US mornings & UK afternoons · Replies within one working day