Life bricks: A chronicle of building an app with AI. | St Louis .

Members-Only

Recent Talks & Demos are for members only

Exclusive feed

You must be an AI Tinkerers active member to view these talks and demos.

October 22, 2025 · St Louis

Vibe Coding: Building Life Bricks

A step‑by‑step walkthrough of building the “Life Bricks” app using Vibe Coding, covering code structure, demo execution, and prompt engineering for LLM analysis.

Overview
Links
Tech stack
  • Groq
    Groq delivers ultra-fast AI inference using its custom-built Language Processing Unit (LPU) to accelerate Large Language Models (LLMs) at scale.
    Groq specializes in high-speed AI inference, leveraging its proprietary Language Processing Unit (LPU) Inference Engine: a chip specifically architected for generative AI and LLMs. The LPU's unique dataflow architecture bypasses the memory and compute bottlenecks of traditional GPUs, delivering consistent, ultra-low-latency performance and superior energy efficiency. This technology, accessible via the GroqCloud platform or on-premise GroqRack clusters, enables real-time application deployment for demanding enterprise customers. Founded in 2016 by former Google engineers (including a lead designer of the TPU), Groq is setting the new standard for real-time AI compute.
  • React
    React is an open-source JavaScript library for building dynamic user interfaces (UIs).
    React is a component-based JavaScript library, developed by Meta (Facebook), engineered for building fast, declarative UIs. It mandates a one-way data flow and utilizes a Virtual DOM mechanism to ensure efficient, predictable updates to the user interface. Developers construct complex UIs by composing small, encapsulated components; this architecture promotes code reusability and simplifies state management across large applications. The library employs JSX (a syntax extension) to integrate HTML-like markup directly within JavaScript logic, supporting development for both web (React DOM) and native mobile platforms (React Native).
  • polygon
    Polygon is the leading Ethereum scaling layer, processing over 3 million transactions daily across its zkEVM and PoS networks.
    Polygon functions as a suite of protocols designed to fix Ethereum's congestion. Its core Proof of Stake (PoS) chain handles high-volume retail traffic for partners like Starbucks and Nike, while its CDK (Chain Development Kit) allows developers to launch custom ZK-powered Layer 2s. By utilizing zero-knowledge proofs and optimistic rollups, the network maintains sub-cent gas fees and 2.1-second block times. It currently secures billions in Total Value Locked (TVL) and remains the primary infrastructure for scaling decentralized applications without sacrificing Ethereum's security.
  • Spoonacular
    The Spoonacular API is a powerful RESTful service: access over 380,000 recipes, 86,000 food products, and a complex food ontology for semantic search.
    Spoonacular delivers a comprehensive food management API: it’s the backend for culinary applications, food trackers, and e-commerce recipe features. Developers gain access to a database of over 380,000 recipes and 86,000 food products, all accessible via a required API key. The system uses a complex food ontology to power intelligent features: semantic search handles natural language queries (e.g., 'gluten free brownies without sugar'), and proprietary algorithms automatically calculate nutritional information. Key endpoints support complex search by ingredients or nutrients, analyze recipe instructions into atomic steps, and even convert amounts (e.g., '2 cups of flour to grams'). This is a complete, well-documented solution for food data integration.
  • RSS
    Really Simple Syndication (RSS): An XML-based web feed format for standardized content distribution and real-time aggregation.
    RSS (Really Simple Syndication, or Rich Site Summary) is a foundational web feed technology: It utilizes a standardized XML file format to publish frequently updated content, like news headlines, blog posts, or podcast episodes. The system allows a publisher to create an RSS document (a 'feed'), which is then monitored by a user's news aggregator (an 'RSS reader') such as Feedly or Inoreader. This process eliminates the need to manually check multiple sites: Users receive timely, consolidated updates directly to a single interface, ensuring efficient, personalized information consumption.

Related projects