GDG Coding Jams
Build with AI. Together.
Share
GDG College Park · United States

GDG AI for Good 2026: Housing — College Park

This week you’re building
🌱
AI for Good

A multi-chapter regional initiative uniting chapters around annually rotating societal challenges to build solutions with Google's applied AI ecosystem.

Full brief for AI for Good →
Concept overview

Uniting chapters around an annual societal challenge

The GDG AI for Good initiative is a multi-chapter regional program across the Google Developer Groups in North America. Rather than running disconnected, one-off hackathons, the initiative unites chapters around an annually rotating societal challenge (such as environmental resilience, digital accessibility, public health informatics, or workforce readiness).

Local chapters host hacking sprints during the Fall period, where developers, designers, students, and domain experts collaborate to build solutions for community-validated problems using Google’s applied AI ecosystem.

Annually rotating societal challenge domains
Environmental ResilienceDigital AccessibilityPublic Health InformaticsWorkforce Readiness
Purpose

Why chapters build together

Bridging Theory and Community Utility

Raise awareness of societal challenges and educate the public on the latest AI tools.

Democratizing Applied AI

Provide a concrete on-ramp for participants to master agent frameworks within AI in an applied, ethical problem space.

Standardizing Regional Excellence

Establish a shared evaluation baseline across chapters, fostering cross-chapter collaboration, talent discovery, and measurable impact tracking.

Broader regional & societal impact

Lasting civic & ecosystem value

Catalyst for Localized Civic Tech

Builds a direct bridge between local non-profits, municipal agencies, and GDG talent, delivering actionable open-source repositories to underserved community partners.

Regional Talent Pipeline & Cross-Pollination

Connects collegiate tech enthusiasts, career switchers, and senior engineers across urban and suburban tech corridors, showcasing regional talent to industry sponsors and ecosystem partners.

100-Point Standard

Generic Universal Evaluation Rubric

4 Pillars × 25 Pts = 100 Pts

This proposed 4-pillar rubric serves as the master scoring guidelines across all chapters and annual iterations to guarantee cross-regional parity.

PillarWeightCore FocusScoring Criteria
1. Problem Validation & Social Impact25 PtsDepth of community relevance, beneficiary focus, and quantifiable real-world value.
  • Problem Definition (10 pts): Clearly addresses the annual topic in an authentic, well-scoped way.
  • Impact Multiplier (10 pts): Demonstrates tangible, measurable benefit to the target audience or community sector.
  • Stakeholder Empathy (5 pts): Solution reflects direct input or realistic personas representing affected end users.
2. Technical Innovation & AI Architecture25 PtsRigor, elegance, and utility of the underlying solution.
  • AI Integration & Necessity (15 pts): Meaningful use of AI (e.g., multimodal inference, agentic orchestration, embeddings) where AI is genuinely necessary, not a gimmick.
  • Architectural Soundness (10 pts): Stable full-stack execution, robust data pipeline handling, clean code structure, and functional working prototype.
3. Responsible AI, Ethics & Accessibility25 PtsSafety, equity, bias prevention, transparency, and inclusive design principles.
  • Safety & Grounding (10 pts): Explicit guardrails against hallucinations, adversarial inputs, bias, and harmful content generation.
  • Privacy & Data Ethics (8 pts): Responsible handling of training data, user confidentiality, and minimal data-collection footprints.
  • Inclusive Design (7 pts): Adherence to accessibility standards (WCAG-aligned UI, keyboard navigation, readable contrasts, screen-reader compatibility).
4. Feasibility, Scalability & Sustainability25 PtsViability of handoff, operational cost management, and long-term ecosystem maintenance.
  • Deployment Viability (10 pts): Low-friction deployment path for resource-constrained community organizations or non-profits.
  • Inference Cost Efficiency (8 pts): Architecture balances token consumption, model sizing, and operational hosting costs sustainably.
  • Documentation & Maintenance (7 pts): Clear setup guides, transparent API dependency mappings, and open-source documentation.
Open source & ownership

Intellectual Property & Open Source Licensing

100% Participant IPApache License 2.0CC-BY 4.0 / CC0

Participants retain 100% ownership of all software, models, and intellectual property created during the event; neither Google Developer Groups (GDG), Google LLC, nor host institutions claim any equity or commercial rights in your work. To ensure community and non-profit partners can deploy, maintain, and scale these civic solutions without legal barriers or licensing friction, all builds submitted to the GDG AI for Good track must be released publicly under the Apache License 2.0, with accompanying project documentation and synthetic evaluation datasets shared under Creative Commons (CC-BY 4.0 or CC0).

Submission terms

Attestation & Showcase Rights

By submitting to codingjam.dev, teams warrant that their build is original work, free of unauthorized third-party or employer-owned proprietary trade secrets, contains no unscrubbed personally identifiable information (PII), and adheres strictly to upstream AI foundation model terms of service. Entrants grant GDG and local organizing chapters a non-exclusive, perpetual, royalty-free license solely to index, demonstrate, screenshot, and publicize the project across regional leaderboards, promotional media, and DevFest showcases.

Right tool, right job

Two tools. Two very different afternoons.

Neither is the beginner option. It comes down to what's already on your laptop, and whether you want a desktop IDE at all. Four questions, then bring the one that fits.

🎨 AI StudioAntigravity 🚀
Undecided — answer the first question.

Already know which one you want?

Your setup

What's on the laptop you'll bring?

The shape of the session

Two hours, four movements.

  1. 0:00 – 0:15
    Intro

    Grab a name tag and a slice, say hello to the instructor, and meet the people either side of you — you'll be asking them things later, so it pays to know their names now. Low pressure, high creativity, ship something messy. Then a quick word on what the room is building tonight, and you're off.

  2. 0:15 – 0:30
    Credits & setup

    The instructor shares the Google Cloud credits with the room. Everyone gets their environment ready — whichever tool they brought. Nobody should be installing anything once the build starts.

  3. 0:30 – 1:35
    Build

    Heads down, and enjoy it — this is the part everyone came for. The agent does the typing; you decide what it's making. Ask the room when you get stuck; someone two seats away hit the same wall ten minutes ago. Want more structure? The codelab walks the spec-driven route — Setup → Plan → Review → Build → API → Verify — but nobody has to follow it.

  4. 1:35 – 2:00
    Share & submit

    Show the room what you made — two minutes, screen-shared from your seat. Half-finished is welcome; the wobbly ones are usually the most interesting. Say what surprised you along the way, and cheer for everyone else while you're at it. Then submit your build before you leave. This is the one thing not to skip — it's what puts your name and your chapter on the showcase, and it takes about two minutes.

Shipped from this jam

2 builds.

Add your build

myRealEstateAgent is an AI home-search and housing tool for College Park, Maryland. It shows the whole city as a 3D map built from real county property records. You can ask in plain English and it finds matching homes, shows them on the map and links each one to Zillow. It also checks which of the city’s 4,000+ single-family lots could legally add a backyard home, estimates the cost and rent, and shows how many homes a zoning change would allow.

“That Gemini picks the tool like search_homes and our code runs it and returns the numbers, having both Gemini and the tool working hand in hand.”

Gemini APIGoogle AI StudioCloud Run

When a developer gets a tax break or other public support, its affordable-housing commitments end up scattered across staff reports, letters, slides, minutes and agreements, and the wording quietly drifts. Promise Ledger reads a deal's PDFs and builds one checked receipt: every commitment with its exact quote and page, how far it got (proposed, supported, signed, delivered), what changed between records, what is missing, and when a term or certificate is due. Gemini only proposes quotes; code ke

“The hard part wasn't getting the AI to find promises; it was stopping it from deciding things. An early model attached a council vote to an unsigned draft letter, so now the model only proposes quotes, and code sets every stage from the record itself.”

Gemini APICloud RunFirebaseFirestoreCloud Storage

Built something at this jam?

Put it on the showcase. It takes two minutes, half-finished is welcome, and your build is credited to this jam automatically.

Share what you built