Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Haystack AI
The talk explores Haystack’s AI-driven low-code platform, focusing on a word-doc-based coding workflow and a Deno-powered system for fast batch execution.
Haystack is a low-code platform that enables sales teams to generate curated leads lists for their GTM and outbound sales processes.
AI-native spreadsheet leverages NLP for sales lead qualification and data enrichment.
- Haystack AIOpen-source AI orchestration framework for Python developers: build, customize, and deploy production-grade LLM applications (RAG, agents).Haystack is the open-source AI orchestration framework from deepset, designed for Python developers building production-ready LLM applications. Its modular architecture uses components (retrievers, generators, agents) to create flexible pipelines for advanced use cases: Retrieval-Augmented Generation (RAG) and autonomous agents. The framework integrates smoothly with major providers (OpenAI, Anthropic) and vector databases (Pinecone, Weaviate), providing the control and tooling necessary to move projects from prototype to enterprise-scale deployment.
- DenoDeno is the secure, modern runtime for JavaScript, TypeScript, and WebAssembly (built on V8 and Rust) that provides a complete, zero-config toolchain.Deno is a simple, modern runtime for JavaScript and TypeScript, created by Node.js founder Ryan Dahl to address key design regrets from Node.js. It operates on the Chromium V8 engine and Rust, prioritizing security by default: file system and network access are explicitly disallowed unless permissions are granted (like browser geolocation). Deno functions as an all-in-one toolchain, offering built-in support for TypeScript, linting, testing, and formatting (`deno fmt`) with zero configuration. It utilizes standard ES module imports via URLs, eliminating the need for a separate package manager like npm and the bulky `node_modules` folder, streamlining dependencies and deployment.
Related projects
AI Startup Scout
Seattle
A sub‑agent scans Hacker News, flags potential startup stories, adds founder data from external sources, and generates concise…
Better Insights into Team Activity
Los Angeles
The session demonstrates a Jupyter Notebook proof‑of‑concept that combines usage‑tracking dashboards, forecasting models, and a retrieval‑augmented LLM to…
Building AI react apps
Seattle
This talk demonstrates building a simple AI app using the Tambo dev tool, enabling AI to control and…
Wild Zebra the AI tutor
Seattle
Learn how we built a Socratic AI tutor, used synthetic users for rapid prompt testing, and optimized multi‑model…
Demo: Dendron - AI-Powered Analysis for Technology/AI Adoption
Miami
Live demo shows multi‑agent LLMs mapping business processes and technology landscapes, maintaining context across analysis and quantifying confidence…
Orchestrating GPTs with Haystack 2.0: Easily Build Cool NLP Apps Like Auto PR and Auto Reno
Berlin
This talk demonstrates how Haystack 2.0 simplifies GPT orchestration to build NLP applications like Auto PR and Auto…