RFQGen: trader chat in, structured RFQ out
An AI solution that reads unstructured trader messages, extracts the RFQ details and drafts the ticket, with GenAI trade suggestions on top. 3rd place in its panel at the Barclays GenAI Hackathon.
- WhenTrader sends a chat message
- ThenLLM extracts the RFQ details
- ThenTicket drafted with trade suggestions
- ResultRFQ ready, no retyping
- Python
- LLMs
- NLP
- Prompt engineering
The problem
A lot of trading still starts in chat. Turning those messages into RFQ tickets by hand is slow, and a request buried in a busy conversation is easy to miss.
What I built
- Led the end-to-end implementation during a 24-hour build with my team, TradeSmith
- An LLM and NLP pipeline that extracts structured RFQ details from unstructured trader communications
- GenAI trade suggestions added to each generated ticket
- Built on sample data provided for the hackathon
Why it matters
It turns free-text chat into structured tickets ready for review, taking manual retyping out of pre-trade work. The project placed 3rd in its panel at the Barclays GenAI Hackathon.
Where it fits
- Customer support triage
- Email-to-order workflows
- Sales operations
- Any team working from messages