Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
The IDE is Dead. Vulcan Ships Our Code Now.
See how an AI dev system orchestrates Claude agents to build, test, and autonomously fix CI failures, managing PRs through a Django backend.
Vulcan is an autonomous AI dev system we built at a stealth startup. It orchestrates Claude Code agents on Mac Minis to execute parallelizable development plans, create PRs, and autonomously fix its own CI failures. We haven’t opened an IDE in months.
I’ll walk through: the plan/phase architecture with dependency graphs for concurrent Claude instances, the worker daemon that spawns and manages Claude Code subprocesses, the self-healing CI loop (including BFS-based loop detection to stop infinite fixes), and how MCP tools let Claude manage its own PR lifecycle through our Django backend.
Live demo: submitting a plan, workers claiming phases, CI breaking, and Vulcan fixing itself.
- 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.
- DjangoDjango is the 'batteries included' Python web framework: high-level, secure, and engineered for rapid, pragmatic development.Django is a high-level Python web framework, built on the 'Don't Repeat Yourself' (DRY) principle, designed to expedite the creation of complex, database-driven applications. It ships with a comprehensive suite of components out-of-the-box: a powerful Object-Relational Mapper (ORM), a robust authentication system, URL routing, and a dynamic, automated admin interface (CRUD operations). This integrated approach minimizes boilerplate code and development time, which is why major platforms like Instagram, Mozilla, and Disqus trust Django for scalable, secure web services.
- PostgreSQLPostgreSQL (Postgres): The world's most advanced, open-source object-relational database (ORDBMS), built for reliability and extensibility.PostgreSQL is the premier open-source ORDBMS, proven over 35+ years of active development. It adheres strictly to ACID properties (Atomicity, Consistency, Isolation, Durability), ensuring data integrity for mission-critical workloads. Key features include robust SQL compliance, Multi-Version Concurrency Control (MVCC), and superior extensibility (e.g., custom data types, functions in multiple languages). Advanced capabilities like native JSON/JSONB support and the PostGIS extension (geospatial data) make it a powerful, flexible choice for complex enterprise applications.
- PRsPRs are the standard protocol for reviewing, discussing, and merging code changes within Git-based version control systems.GitHub pioneered the Pull Request in 2008: it transformed software development by centralizing code review. A developer initiates a PR to propose changes from a head branch to a base branch (usually main). This action triggers automated workflows: CI/CD pipelines run unit tests while peers provide line-by-line feedback. Industry leaders like Google and Meta use similar "Change Request" patterns to maintain stability across massive codebases. Every PR serves as a permanent audit trail for the project's evolution.
- Claude Code SDKThe programmatic interface for Claude Code: build production-ready AI agents with full access to code execution and rich tool use.This is the Claude Code SDK (also known as the Claude Agent SDK): the core agent harness now available as a library (TypeScript and Python) for production systems. It lets you integrate Claude's agentic capabilities—like file operations, code execution, and web search—directly into your developer tools and scripts. Leverage built-in features like automatic context management and the Model Context Protocol (MCP) for powerful, enterprise-ready integrations with external systems like Jira or Slack. Deploy sophisticated agents, such as SRE agents for diagnosing production issues or security review bots for auditing code, with fine-grained control over permissions and capabilities.
- MCPMCP is the open-source standard for securely connecting AI agents (like LLMs) to external tools, data, and enterprise workflows.The Model Context Protocol (MCP) functions as a standardized integration layer: think of it as a USB-C port for AI applications. Developed and open-sourced by Anthropic, this protocol allows large language models (LLMs) to access real-time context and execute actions via external tools like GitHub, Jira, or proprietary databases . It uses a simple JSON-RPC interface to define tools, schemas, and endpoints, which enables AI agents to perform complex, state-changing tasks—such as creating a GitHub issue or running a test script—rather than just generating text . MCP is essential for building agentic AI systems that can autonomously pursue goals and operate within defined safety and permission boundaries .
- GitHub API + WebhooksAutomate workflows by triggering real-time HTTP callbacks from GitHub repository events directly to your infrastructure.GitHub Webhooks transform passive API polling into an active event-driven architecture. By subscribing to specific triggers (like 'push', 'pull_request', or 'release'), your server receives a JSON payload the millisecond an action occurs. This eliminates unnecessary GET requests and reduces latency for CI/CD pipelines, Slack notifications, and automated deployments. Pair these hooks with the REST or GraphQL APIs to programmatically manage issues, mirror repositories, or update commit statuses across your entire organization.
- Python/TyperTyper is a library for building CLI applications based on Python type hints.Built by the creator of FastAPI, Typer leverages Python 3.6+ type annotations to generate sophisticated command line interfaces with minimal boilerplate. It provides automatic help documentation, shell completion for bash/zsh/fish, and deep integration with VS Code and PyCharm. By using standard Python types like int, str, and Path, developers get full editor support and validation without learning a complex DSL (Domain Specific Language).
- Rich (terminal UI)A Python library for writing rich text and beautiful formatting to the terminal.Rich delivers high-end CLI aesthetics through a simple API (pip install rich). It handles complex terminal tasks like syntax highlighting for 200+ languages, markdown rendering, and dynamic progress bars with ease. The library supports 16.7 million colors (Truecolor) and includes built-in components for tables, logs, and tracebacks. By providing automatic word-wrapping and layout management, Rich ensures Python command-line applications look professional across various terminal emulators.
- Mac Mini hardwareApple's compact desktop powerhouse featuring M4 and M4 Pro silicon in a 5 by 5 inch footprint.The Mac Mini hardware delivers massive performance density through Apple's latest M4 series chips. The base M4 model handles everyday workflows with ease, while the M4 Pro configuration supports up to 64GB of unified memory and 273GB/s bandwidth for heavy creative tasks. Connectivity is professional grade: the rear panel hosts three Thunderbolt ports (Thunderbolt 5 on M4 Pro), HDMI, and Gigabit Ethernet. Despite its diminutive 5-inch square chassis, the thermal architecture maintains peak clock speeds during sustained 4K video renders or complex compiles. It is the most versatile entry point into the macOS ecosystem for users who demand desktop reliability without the bulk.
Compose Email
Loading recent emails...