Fourth & Hope

HopeHub

From spreadsheets to grant-ready data

I helped translate staff research into a nonprofit CRM and designed the grant-report workflow that the team connected to Firestore and Gemini.

Role: Product designer — research, workflows, interface
Timeline: Weekend hackathon
Methods: Staff interview, service mapping, prototyping
Technical collaboration: Gemini API, Firebase Firestore

Watch the presentation and view the winning project on Devpost

HopeHub staff dashboard shown in a green presentation layout

Adoptedteam-reported use by Fourth & Hope after the hackathon

Geminiturns tracked outcomes into grant-report drafts

Real timeservice and outcome tracking through Firestore

Fourth & Hope had no shared view of daily services.

Staff tracked showers, meals, laundry, shelter, and medication across separate spreadsheets. The fragmented workflow made basic coordination difficult and left leadership without measurable outcomes for funders.

An interview with staff made the need concrete: log services quickly, keep client information together, and turn the work already happening into evidence the organization could use.

Interview findings showing gaps in service tracking, workflow, grant outcomes, and communication — Staff interviews connected daily workflow friction to the organization’s ability to secure funding.

I helped design one workflow for service, client, and outcome data.

I worked across the research and design process, helping translate staff needs into a client directory, announcements, live service logs, and profiles that kept demographics, medication, and service history together.

The mid-fidelity dashboard added real-time queues and wait times. I collaborated with the developers on the information structure and interaction flow while they implemented the full-stack application and Firestore data layer.

The staff dashboard makes current demand visible while the client profile preserves service history.

We connected tracked outcomes to a Gemini-assisted report pipeline.

The harder design problem was not simply displaying data. Funders need a coherent account of reach, outcomes, budget use, highlights, and next-quarter goals, while staff naturally produce service logs throughout the day.

I helped define the reporting experience and the information it needed to surface. The developers connected the analytics workflow to the Gemini API: the prototype sent structured Q1 metrics to Gemini 2.0 Flash, formatted the response as a grant report, compiled it to PDF, and returned it as a download.

This kept my contribution accurate: I did not build the backend integration, but I helped design the path from staff-entered data to a useful, reviewable report. Human review remained essential before any submission.

HopeHub solution slide showing the centralized CRM screens — Service tracking and reporting live in the same system, so evidence is captured as work happens.

Fourth & HopeIllustrative Gemini-assisted grant report

Reporting periodQ1 2025Generated April 19, 2025

487People served

3,120Meals served

92%Bed occupancy

18Housing transitions

14Program completions

11Job placements

Program highlights

Expanded the kitchen team to provide vegetarian meal options.
Four program graduates returned as volunteer mentors.
Launched the Hope Garden therapy initiative with a local church.

Goals for next quarter

Pilot a job-training workshop for shelter residents.
Increase bed capacity by 10%.
Implement digital intake forms for faster check-ins.

Prototype workflow: Firestore metrics → Gemini 2.0 Flash → structured LaTeX → downloadable PDF → staff review

This preview uses the prototype’s mock Q1 data to show the structure Gemini received and the kind of narrative staff could review. It is an illustrative portfolio reconstruction, not a submitted grant report.

The next iteration starts with what I learned.

In a next iteration, I would validate the report structure with grant staff, test Gemini outputs against a consistent rubric, and make the human review step explicit before export. I would also establish the component library earlier so design and development could move faster without introducing inconsistencies.