
About the Buildathon
Re‑imagine the command line as your personal AI studio. In a fast 4‑hour sprint, teams will prototype headless AI agents and workflows that call the Google Gemini CLI / API to do useful, locally grounded things.
Why local? Because the most valuable AI often starts close to home—where your notes, data, and daily tools already live. Think:
- Research Wrangler: Sweep a downloads folder full of PDFs, auto‑extract key findings, build structured notes.
- Story Forge: Generate a custom bedtime story plus image assets saved to disk and ready to AirDrop to a tablet.
- Writing Stitcher: Feed a plain‑English outline + scattered markdown notes; have Gemini assemble a cohesive short story.
- CLI Lab Assistant: Natural‑language wrapper around shell commands that can search, transform, and summarize project files.
- Data‑Aware Agents: Use local CSVs, logs, or config files to personalize outputs, alerts, or dashboards.
Bring whatever local data you’re comfortable using. Synthetic / sample data is fine.
☝️ RSVP now. Space is limited. ☝️
Who is this for?
- Startup builders exploring personal AI tooling.
- ML engineers & data folks curious about local agent workflows.
- CLI power users who script everything.
- Students / researchers who want fast, scrappy prototyping with foundation models.
- Designers / storytellers who like mixing assets, prompts, and automation.
All skill levels welcome; cross‑functional teams often ship the coolest stuff.
What to Bring
- Laptop with terminal access.
- Local files or sample data you can legally use.
- GitHub account.
- (Optional) APIs, sensors, or tools you want to integrate.
We’ll provide: Gemini CLI quickstart, starter repo scaffolding, sample prompts, and office‑hours style roaming mentors.
Submission Requirements
To be eligible for judging, each team must submit by 3:00 PM (local) on September 6th:
1. Code Repository
Public or invite‑only (grant judge access). Include install + run instructions.
2. ≤ 3‑Minute Demo Video
Screen‑capture is fine. We must see it run: what it does, how Gemini is used, what local resources it touches, and why it matters.
3. Short README Checklist
Include: problem/use case; how to run; where Gemini is called; what’s local; what’s hard/interesting; what’s next.
Optional Extras: sample outputs, test scripts, or a small dataset to reproduce.
What is AI Tinkerers?
AI Tinkerers is a meetup exclusively for practitioners with technical, machine learning, and entrepreneurial backgrounds who are actively building and working with foundation models, such as large language models (LLMs) and generative AI. If you’re deeply passionate about creating LLM-enabled applications, have hands-on experience in building such systems, and want to connect with like-minded people who share your level of commitment, then this group is the perfect fit for you. With AI Tinkerers meetings happening in many cities, we support a dedicated global community.
when
LoCATION
agenda
10:00 AM – Doors open
11:00 AM – Kick‑off + Google Gemini CLI Demo / Quickstart
11:30 AM – Team formation / environment checks / idea lock‑in
12:00 PM – Working lunch (keep building)
12:15–2:45 PM – Build window (mentor loops, tech help)
2:45 PM – Code freeze / capture demo video
3:00 PM – Submissions due (repo + ≤3‑min demo video)
3:15 PM – Quick judging & lightning demos (select teams)
4:00 PM – Wrap / swag codes follow.

