CivicAI: Making City Repair Reports Easier to Prioritize

Description and use

CivicAI is a prototype that uses Gemini to structure citizen-submitted photos of infrastructure issues and calculates a transparent priority score for repair triage.

Problem

City teams need a way to review public infrastructure reports and prioritize repairs based on structured information extracted from photos.

Outcome

CivicAI prototype demonstrates how AI can structure citizen reports and provide a transparent priority score, improving triage transparency over simple arrival order queues.

Workflow

• 1. Citizen submits photo and location via web form.
• 2. Frontend (React/TS/Vite) sends data to Node.js/Express API.
• 3. API forwards image to Gemini for structured JSON response.
• 4. If Gemini fails, demo response is used.
• 5. API calculates priority score from severity, report count, age, location importance, and AI confidence.
• 6. Dashboard displays issue details, map view, and summary analytics.
• 7. Reviewer can view factors influencing priority and suggest improvements.

Evidence

A citizen can submit an issue with a photo and location. The backend can send the image to Gemini for a suggested issue type, severity, confidence, responsible department, risk factors, and recommended action.

Source

CivicAI also calculates a priority score from five factors: severity, number of reports, how long an issue has remained unresolved, location importance, and AI confidence.

Source