Why it matters
A complete prototype-to-deploy path in one afternoon. For developers who haven't shipped an LLM app end to end, the Gemini-Streamlit-Cloud Run stack is one of the lowest-friction routes from idea to a working URL.
The tokenmaxxing angle
The session leans on 'high-performance, low-latency models like Gemini Flash' - the budget tier of Google's lineup. Choosing Flash over Pro is model routing 101: matching the cheapest adequate model to the job is the core tokenmaxxing move.
From the organizers
Saturday June 27, 2-4pm PDT at Palms - Rancho Park Branch Library, 2920 Overland Ave, LA. Part of the community-led 'Build with AI' series; covers Streamlit, Gemini API integration, and Cloud Run deployment.