Using AI to reverse-engineer years of user stories from a Salesforce org
I had the idea of using AI to reverse engineer years worth of user stories from the code / metadata / documentation of a Salesforce org. Ryan McCloskey, as he so often does, took that idea and systematized / ran with it.
It will require some human refinement, but thanks to Ryan plus Cursor, we now have a CSV full of "As role X, I need Y so that Z" and every one I've read so far makes perfect sense and traces back to a legit business requirement.
Doing that from scratch would have been a slog, and prone to missing those little solutions added years ago by a contractor based on a phone call upon which critical business operations rely.
Jessie Grenfell
Jessie has spent 20+ years architecting and delivering software for organizations where complexity is the norm: financial services, insurance, nonprofits, and regulated industries where getting it wrong isn’t an option. She specializes in the hard problems: unique operational workflows, cross-system integrations, and compliance requirements (HIPAA, CCPA, SOC 2) built into the design from the first conversation.
Her AI work comes out of that background. She has shipped AI to production, not just piloted it: a multi-agent research pipeline that cut a client’s investigation time from over an hour to minutes, and natural-language analytics that let executives ask plain-English questions of their operational data and get validated charts back. Years building business critical systems taught her where AI belongs in a business process and where it doesn’t.
At Codality, she leads engagements from discovery through delivery, because she’s seen what happens when that thread gets cut.