Contact Card Extractor
Thomas - Product Creator
June 2022
The Client.
Sales agents that engage with leads through email.
The Problem.
Email is very busy. It has attachments, text, etc... It is not easy to read. And it takes a long time to open and load. Even more, when you are looking for contact information in emails it gets even tougher. It's like finding a needle in a haystack!
The Solution.
Using the GPT3 model and a built in natural language parser, this service extracts contact info from an email and converts it into a Vcard format. The Vcard is emailed back to you as an attachment.
The Process.
First I needed to make sure this will actually work pretty well. Can I take an email and extract contact information accurately? What model will I use and how will I ultimately process the text?
Nothing is better these days for rapid NLP prototyping than OpenAI’s text-davinci-002 model. I copied and pasted an email I received from someone the other day trying to market outsourced developers.
After confirming that the model would work, I performed the trivial task of wrapping this functionality in a full-stack app. The rest, as they say, is history.
The Result.
I ended up with a perfectly functioning SaaS to receive emails, parse them to generate a vCard, and email back the vCard to the original email receiver.
