Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
The non-technical builder
Learn how non-technical builders can create full prototypes for product teams, showcasing examples like a ride overview feature and a content studio for managing brand personality.
I used to think not knowing coding was my biggest limitation as a product owner. I now realize I don’t need to know it. While building Ride with Dave, I’ve been able to build full prototypes that I can hand to my team for sanitizing and putting into production. I can show two examples of this: Dave’s “postcard” feature, which creates ride overview for users, and Dave’s “content studio” which shows how we manage Dave’s personality across social media.
- Google AI StudioThe web-based developer platform for rapidly prototyping and building AI applications with the Gemini family of multimodal models.Google AI Studio is your dedicated, browser-based environment for building with Gemini, Google's next-generation multimodal AI models. It provides a unified playground to test prompts across text, image, and video modalities: no server setup or complex configuration required . Developers move quickly from concept to functional app, leveraging features like chat prompts, real-time streaming, and function calling . Once a prototype is validated, the platform offers one-click code export to seamlessly transition to the Gemini API for production deployment .
- GeminiGoogle's natively multimodal AI model: understands and operates across text, code, audio, image, and video.Gemini is Google's most capable and general AI model, engineered from the ground up to be natively multimodal: it seamlessly understands and combines information across text, code, audio, image, and video inputs. The technology is optimized for flexibility, running efficiently on everything from data centers to mobile devices. It is deployed in three key sizes: Ultra (for highly complex tasks), Pro (for broad scaling), and Nano (for efficient on-device tasks). Developers access this power via the Gemini API to build next-generation applications.
- NanoBananaNano Banana (Gemini 2.5 Flash Image) is the state-of-the-art AI model for rapid, conversational image editing with unmatched character consistency.Nano Banana, powered by Google's Gemini 2.5 Flash Image API, is a next-generation AI image editor. This technology excels at complex, multi-turn creative workflows: simply upload an image and describe your desired edits (e.g., 'place the creature in a snowy mountain'). It delivers flawless results in seconds, operating up to 8x faster than previous models. Key capabilities include superior character consistency, multi-image fusion for seamless composition, and high-resolution output (up to 4K in the Pro version). The model leverages Gemini's deep world knowledge for precise visual reasoning and complex diagram interpretation, making it ideal for professional and commercial projects.
- Meta Graph APIThe primary HTTP-based interface for programmatically querying data, posting stories, and managing ads across Facebook, Instagram, and WhatsApp.This RESTful API serves as the central gateway to the Meta Social Graph: a vast network of nodes (users, photos, pages) and edges (comments, likes, tags). Developers use standard HTTP methods to interact with specific versioned endpoints (v19.0 is the current stable release). Whether you are pulling real-time Instagram insights, automating WhatsApp business messages, or managing complex Facebook ad campaigns, the Graph API provides a unified structure for data exchange. It relies on OAuth 2.0 for secure access tokens and returns structured JSON responses, making it the essential tool for any application integrating with Meta’s 3.9 billion monthly active users.
- Garmin APIGarmin APIs provide high-resolution health and fitness data from millions of wearables to third-party platforms via secure, RESTful integrations.The Garmin Connect Developer Program offers four primary integration paths: Health API, Activity API, Women's Health API, and Training API. These tools allow developers to sync over 30 specific metrics (such as VO2 max, Sleep Score, and Pulse Ox) from devices like the fēnix and Forerunner series. The architecture utilizes OAuth 2.0 for authentication and relies on real-time webhooks to push data immediately upon device sync. This setup supports a global user base of over 66 million active accounts, providing precise biometric insights for corporate wellness, insurance, and clinical research applications.
Related projects
TriCoach
Boston
Learn how an AI coach built with Claude Code and deployed on Vercel helps train for triathlons, adapting…
An engineering team in your pocket
Ho Chi Minh City
Learn about CAR, a meta-harness for coding agents that enables multi-hour builds, self-hosted on your own hardware, for…
Roundtable Demo Video | Discover innovations and researchers for your business
Seattle
Explore how a structured backend influences unstructured LLM output, using a roundtable demo of an AI marketplace for…
Five minutes to get ready
Seattle
Learn how to build a mobile app that uses OpenAI agents and Supabase to deliver pediatric emergency stats,…
Make Vibe Coding Actually Ship
Manchester Nh
See how a structured loop, separating ideation, specification, and execution with AI tools, turns AI ideas into working…
Sales Intelligence Assistant
Seattle
Learn a step‑by‑step workflow that extracts web and PDF content, converts it to markdown, chunks it, and stores…