Citi · Wealth Onboarding · 2025

Doculigence

GenAI document extraction · Citi hackathon

A hackathon build for the wealth onboarding team that turns client documents into structured data, with every field linked back to its source.

  • Python
  • GenAI
  • React
onboarding document processing
Faster
every field linked to its source
Traceable

The problem

Pulling client data out of onboarding documents was manual and slow.

What I built

  • GenAI extraction of client data from documents into structured JSON
  • An accountability UI that back-links every extracted field to where it came from

Built at Citi. Descriptions stay at the level of problem, capability and outcome. No internal data, algorithms or client details are shared.

Want to talk about systems like this?

Email me