← back
Git push get an AI API: Ryan Fox-Tyler
Takeaway
Productionizing AI features means composing functions, models, and traditional code/dictionary validation — git push is the deploy primitive.
Summary
- Hypermode workshop builds AI features via iteration: starts with a 'Hyper Categories' multiplayer game using AI to score uniqueness and cluster similar answers.
- Validation requires a mix of model + traditional code — e.g., 'P doctor' for occupation+letter P needed a dictionary check on top of LLM judgment.
- Second example: GitHub issue triage template deployed via Hypermode (just-ship.ai) showing AI building blocks composed as functions + models + data sources.
- Stack includes similarity search across user responses, embeddings, model hosting via Hypermode — git push deploys the AI API.
hypermodeai-platformtriage
Original description
In this workshop you’ll build a demo that augments an app with AI for classification, natural language search, summarization, and outlier detection. Then you’ll learn how to iteratively improve before and after shipping to prod. We’ll use Hypermode to move fast and reduce infra overhead. You’ll walk away with a greater intuition for when & how to integrate AI without refactoring. Also, we have swag. Recorded live in San Francisco at the AI Engineer World's Fair. See the full schedule of talks at https://www.ai.engineer/worldsfair/2024/schedule & join us at the AI Engineer World's Fair in 2025! Get your tickets today at https://ai.engineer/2025 About Ryan Product creator Leading teams building devtools Now at Hypermode I'm on a mission Make each dev an AI eng Skip data science