NotAWrapper

About the project

NotAWrapper is an AI-powered benefits navigator built to help people understand whether they may qualify for public support programs and what they should do next.

We focused on a simple problem: public benefit systems are often difficult to navigate, full of fragmented information, technical eligibility language, and unclear next steps. Many people who need help do not just need a list of programs — they need a way to understand which ones might apply to their situation.

Our project addresses that gap by turning confusing eligibility rules into plain-language guidance. Instead of acting as a static directory, NotAWrapper asks relevant questions, interprets a user’s situation, and provides personalized guidance on possible eligibility and recommended next steps. This directly matches the Benefits Navigator challenge direction for helping users interpret rules and reduce confusion.

Inspiration

The inspiration came from how overwhelming public support systems can feel, especially for people already dealing with financial stress, childcare needs, healthcare uncertainty, or emergency situations. Even when support exists, the path to finding the right program is often buried behind bureaucratic wording and disconnected websites.

We wanted to build something that feels less like searching through government documentation and more like talking to an intelligent guide. The goal was to create a tool that helps users answer practical questions such as:

Do I likely qualify?
What information matters for eligibility?
What should I prepare before applying?
What should I do next?

How we built it

We built NotAWrapper as a web-based MVP with a conversational interface that guides users through eligibility discovery in a more natural way.

The core flow works like this:

The user describes their situation or need.
The system asks follow-up questions to gather the most relevant context.
It translates program-style requirements into plain English.
It returns a personalized assessment of possible eligibility.
It suggests next steps, such as what documents to prepare or which type of support to pursue.

From a product perspective, the main emphasis was not just information retrieval, but interpretation. We wanted the system to reason through user context and present guidance in a way that is understandable and actionable.

Challenges we ran into

One of the biggest challenges was balancing usefulness with responsibility. Benefit eligibility can be nuanced, and many programs depend on edge cases, local rules, documentation requirements, and exceptions. Because of that, the system needed to be helpful without sounding falsely certain.

Another challenge was designing the questioning flow. Asking too few questions makes the guidance vague, but asking too many questions creates friction and makes the experience feel like paperwork. A lot of the work went into finding the right balance between precision and usability.

We also had to think carefully about trust. For a project like this, clarity matters as much as intelligence. The wording, explanations, and next-step recommendations all needed to feel supportive, transparent, and easy to follow.

What we learned

This project taught us that building useful AI for civic and public-good applications is as much a UX problem as it is a technical one. A strong model alone is not enough — users need explanations they can trust, flows that reduce stress, and outputs that are actionable.

We also learned the value of translating complexity into plain language. In this space, success is not about sounding smart; it is about helping users make better decisions with less confusion.

Most importantly, we learned that AI can create real impact when it lowers barriers to access. If a person can move from “I have no idea where to start” to “I know what I may qualify for and what to do next,” then the product is doing something meaningful.

What’s next

The next step for NotAWrapper would be expanding the breadth and depth of supported benefits, improving rule coverage, and making recommendations even more personalized. Future iterations could also support community organizations, caseworkers, and nonprofits that help people navigate these systems at scale.

NotAWrapper is ultimately about making support systems easier to understand, easier to access, and less intimidating for the people who need them most.