Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Promptspace
Learn how to visualize, debug, and optimize multi‑prompt LLM workflows using a node‑based UI that tracks token usage, latency, and cost.
Think of prompt chains as interconnected LLM calls - each processing data and passing it along. When you’re working with 20 different prompts across files, you can’t see how they interact or where to optimize. That’s the core technical challenge - finding ways to visualize these complex interactions intuitively.
I built specialized nodes to handle different data types - table nodes for structured data, text nodes for prompts, eval nodes for testing. Using React Flow and Next.js, you can instantly see how data transforms as it flows through your chain. The interesting engineering problems came from making complex data easily visualizable and actionable in the UI.
Each node tracks crucial metrics - token usage, latency, cost - exposing performance issues instantly. The backend manages template versioning and chain validation, while we run extensive testing on nodes and full chains.
On the surface, it’s just drag-and-drop simple with nodes and connections. But underneath, there’s a lot going on to make these prompt chains reliable and efficient.
Promptspace: AI extracts structured data from text; React Flow visualizes.
- React FlowThe highly customizable React component for building node-based editors, interactive diagrams, and flowcharts.React Flow is the powerful, open-source (MIT-licensed) library for creating interactive node-based UIs in React applications. It ships ready-to-use with core features like dragging, zooming, panning, and multi-selection, letting you focus on application logic. Developers use it to build complex tools: workflow automation builders, no-code platforms, and data visualization dashboards. Major companies, including Stripe and Typeform, rely on React Flow for their production environments, validating its flexibility and robust feature set.
- NextNext.js is the full-stack React framework: it delivers high-performance web applications via hybrid rendering and powerful, Rust-based tooling.This is the React Framework for production: Next.js enables you to build full-stack web applications with zero configuration and maximum efficiency. It supports a hybrid rendering approach (Server-Side Rendering, Static Site Generation, and Incremental Static Regeneration) for optimal speed and SEO performance. Key features include React Server Components, Server Actions for running server code directly, and the App Router for advanced routing and nested layouts. Developed by Vercel, it leverages Rust-based tools like Turbopack and the Speedy Web Compiler for the fastest possible builds and a superior developer experience.
- PromptSpacePromptSpace is the GenAI app store and development platform, leveraging its declarative PSL (PromptSpace Language) to deploy complex applications in minutes.PromptSpace is your command center for rapid GenAI application deployment: go from idea to a published app in minutes. The platform uses PSL (PromptSpace Language), a declarative orchestration tool, to define unique user experiences without the complexity of UI libraries or job queues. It supports single-line calls to major models (GPT-4, ElevenLabs, Stable Diffusion). The efficiency is proven: the team scaled MakeLogo.ai to a $100k run rate using PSL, reducing a month of UX work to a single day. PromptSpace handles the infrastructure, ensuring immediate user feedback collection.
- LLMsLarge Language Models (LLMs) are Transformer-architecture deep learning systems (e.g., GPT-4, Llama 3) trained on massive text corpora to generate, summarize, and reason over human language at scale.LLMs are advanced deep learning models, specifically Generative Pre-trained Transformers (GPTs), designed to process and generate human-like text. They are trained on vast, multi-trillion-token datasets, giving them billions of parameters to learn complex linguistic patterns (syntax, semantics). This scale enables emergent capabilities: few-shot learning, code generation, and complex reasoning. Key examples include OpenAI's GPT-4, Google's Gemini, and Meta's Llama 3. LLMs power applications from conversational AI (ChatGPT) to automated content creation, fundamentally shifting how machines handle unstructured language.
Related projects
Mandark
Singapore
Explore how Mandark's extensible architecture enables a simple, code‑generation assistant that reduces reliance on retrieval‑augmented generation through new…
Nuance
Singapore
Learn how a virtual project manager agent uses Gemini models and Mastra framework to automate context management, task…
cupertino.ink
Singapore
Learn how to set up cupertino.ink, a local server for Apple hardware that runs MCP tools using a…
Prompt To Production - Copilots in UI Development
Abu Dhabi
Learn how to leverage AI copilots for consistent and efficient web development, maximizing their potential for modern UI…
AI Prompt Templates You Can Share and Take Anywhere
Seattle
Learn to build and share portable AI workflows as single-file HTML Saayn Notebooks—browser-run, vanilla-JS, web-component demos for blog…
PromptPilot
Rio De Janeiro
The talk explains PromptPilot’s architecture, visual precision challenges, debugging tools, and its two‑stage macro/micro targeting for real‑time coordinate-based…