I am helping a not-for-profit, [NavSahyog](https://navsahyog.org/), build a custom software for their entire operations and programs that also tracks longitudinal impact. The organization conducts programs for children in Indian villages after school to build live skills.

This is my second iteration because the first version felt like a simplistic fit and improvement over their existing vendor provided app.

I have now designed a domain model based on my understanding and observations. I have a day job so I can't spend a lot of time in sync with the team. I have created a web app where the NGO management can test scenarios (by recording voice), and the AI (Claude Agent SDK) runs it past the domain model. In case, there is a gap, they can persist the scenario. After every iteration, I read through the scenarios and assimilate them into the domain model.