Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Shotgun: Spec-Driven Development
See Shotgun turn your repo into a queryable code graph. It generates precise, code-aware specs and executable tasks for AI agents, all live in a TUI.
A live, TUI‑only, code‑first walkthrough of Shotgun—the open‑source assistant that turns your repo into a live, queryable code graph and then uses Agentic workflows to produce deep, codebase‑aware research and implementation‑grade specifications. In minutes it explodes those specs into precise, agent‑ready task lists you can hand directly to AI coding agents. We’ll index a repo, ask repo‑scoped questions, generate detailed specs with traceability to code, create executable tasks, and show just enough internals to prove how it works.
This was largely built using Claude Code. After the shotgun was able to generate specs/research we used the Shotgun to generate specs to give to Claude Code to build the Shotgun itself. Also it’s open-source and 100% in Python, contributors are welcome.
Shotgun generates codebase-aware specs using tree-sitter indexing for AI coding agents.
Shotgun builds a live code graph to ground AI agent specifications.
- Claude CodeAnthropic's agentic coding tool: Unleash Claude's raw power directly in your terminal or IDE to turn complex, hours-long workflows into a single command.Claude Code is Anthropic’s powerful agentic coding assistant, designed for high-velocity development. It operates natively within your terminal, IDE (VS Code, JetBrains), or via a web interface, allowing you to delegate complex tasks like feature building, bug fixing, and codebase navigation. The agent plans, edits files, executes commands, and creates commits, maintaining awareness of your entire project structure. Internally, Anthropic engineers using Claude Code reported a 67% increase in productivity, demonstrating its capacity to deliver significant gains for Pro and Max plan users.
- OpenAI APIOpenAI API: Your direct gateway to cutting-edge AI models (GPT-4o, DALL-E 3, Whisper), enabling scalable, multimodal intelligence integration into any application.The OpenAI API provides authenticated, programmatic access to a powerful suite of generative AI models. Developers leverage REST endpoints and official libraries (Python, Node.js) to integrate capabilities like advanced text generation (GPT-4o), image creation (DALL-E 3), and speech-to-text transcription (Whisper). This platform is engineered for scale, supporting millions of daily requests for tasks from complex reasoning to real-time customer support agents, ensuring your application gets reliable, state-of-the-art intelligence.
- Anthropic APIProgrammatic access to Anthropic's Claude models (Opus, Sonnet, Haiku) for complex reasoning, vision, and tool-use applications.The Anthropic API delivers programmatic access to the Claude model family (Opus, Sonnet, Haiku), enabling developers to integrate state-of-the-art AI into applications. Use the Messages API for conversational tasks, leveraging Claude 3.5 Sonnet for balanced performance or Claude 3 Opus for complex analysis. Key features include Tool Use (function calling), Vision capabilities for image analysis, and a large 200K token context window for extensive document processing. This API provides a powerful, reliable foundation for next-generation AI projects.
- 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.
- tree-sitterAn incremental parsing library that builds concrete syntax trees and updates them efficiently during live editing.Tree-sitter generates robust syntax trees using a C-based runtime and language-specific grammars. It supports over 40 languages (including Rust, JavaScript, and Python) to power features like syntax highlighting and code navigation in Neovim and GitHub. The engine handles syntax errors gracefully and re-parses modified code in O(log n) time. This efficiency ensures immediate feedback without blocking the main editor thread.
Related projects
Paradigm – Understand the Code You Don’t Understand
Poland
Understand legacy code with Paradigm, a developer tool for deciphering unfamiliar systems, from old bank code to recent…
OpenSpec: Creating an open source spec driven development framework that's pluggable into any AI coding tool
Sydney
Learn how a spec‑driven workflow treats specifications as code, enabling testing, maintenance, and faster safe shipping, with real…
How Not to Kill Anyone: Safety Layers in Medical Reasoning
Poland
Methods for extracting body composition and lab data from unstructured sources, building real‑time digital health twins, and ensuring…
Teachable AI Agents in Software Development
Poland
Learn how to build AI agents that continuously adapt to development workflows, using practical techniques and best practices…
How I hacked the hottest SF startup
Poland
Discover how Poke's system prompt was leaked and its architecture reverse-engineered, offering a glimpse into future AI interactions…
Genaicode - programming on steroids
Poland
Live demo of Genaicode, an AI code generator, modifying a personal game in real time and covering latency,…