michaelml.dev / Michael_Portfolio.ipynb
Neighborly is a mutual-aid app that makes helping local communities simple. Users can offer or request items, services, or time, while organizations can post shortages directly. AI agents highlight the top 3 urgent needs nearby, balance supply and demand, and keep posts safe and trustworthy.
[ ]
code · Neighborly
project = load_project("neighborly")
project.summary()Output
Neighborly
Neighborly is a mutual-aid app that makes helping local communities simple. Users can offer or request items, services, or time, while organizations can post shortages directly. AI agents highlight the top 3 urgent needs nearby, balance supply and demand, and keep posts safe and trustworthy.
ReactTailwindCSSSupabaseGoogle-ADKPythonRAGPostgreSQLReal-time SyncGeospatial DataAgentic AI
[ ]
code · Problem definition
project = load_project("neighborly")
project.problem()Output
ProblemPeople and local organizations want to exchange help, but offers, requests, urgency, and trust are difficult to coordinate.
ApproachBuild a React and Tailwind interface on Supabase, then use Google ADK agents for urgency ranking, supply-demand matching, and trust checks.
OutcomeDelivered a working mutual-aid prototype with real-time posts, nearby priority needs, matching, and automated moderation; no adoption metric is claimed.
[ ]
code · Constraints
project = load_project("neighborly")
project.constraints()Output
Constraints
- Urgency and trust decisions needed grounding in local post context.
- Offers and requests changed in real time and depended on location.
- Automated moderation needed to support rather than replace community judgment.
[ ]
code · Role and implementation
project = load_project("neighborly")
project.implementation()Output
Role and implementation
My role: Helped build the agent-supported community workflow and connect the React/Tailwind product, Supabase data layer, and Google ADK services.
- Built the mobile-first experience with React and Tailwind CSS.
- Used Supabase for PostgreSQL-backed real-time data synchronization.
- Implemented Google ADK agents for urgency, balance, and trust workflows.
[ ]
code · Architecture
project = load_project("neighborly")
project.show_architecture()Output
Community EngagementUsers and Organizations submit offers, requests, and events via accessible UI
Data Ingestion & SyncReal-time intake of user posts and synchronization with Org CSV/API feeds
Urgency AnalysisAI agents analyze context to tag urgency and identify the top 3 critical needs nearby
Supply-Demand MatchingIntelligent balancing of available resources with current community needs
Trust & SafetyAutomated moderation and verification to ensure a safe community environment
Smart DistributionDelivering prioritized, relevant updates to neighbors who can help
[ ]
code · Demo and media
project = load_project("neighborly")
project.media()Output
[ ]
code · Evaluation
project = load_project("neighborly")
project.evaluation()Output
Evaluation
- Exercised the offer, request, shortage, ranking, and matching paths in the prototype.
- Kept outcomes framed as product behavior because no deployment study is documented.
[ ]
code · Results
project = load_project("neighborly")
project.results()Output
Results
- Produced a functioning prototype that surfaces three urgent nearby needs and coordinates offers with requests.
- No user-adoption or community-impact metric is claimed.
[ ]
code · Tradeoffs and failures
project = load_project("neighborly")
project.tradeoffs()Output
Tradeoffs
- Automated ranking can improve responsiveness but must remain transparent and contestable.
- Real-time geospatial features introduce privacy and moderation considerations.
[ ]
code · What I would improve
project = load_project("neighborly")
project.improvements()Output
Improvements
- Test ranking quality with community organizations and publish moderation criteria.
- Add privacy-preserving location controls and operational escalation paths.
[ ]
code · Links and repository
project = load_project("neighborly")
project.links()Output