Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Claude-Reflect: Coding Agent Memory
Learn how Claude-Reflect creates persistent memory for coding agents through corrections, a two-stage pipeline, and reusable `/reflect-skills` via a live demo.
I will show how claude-reflect turns day-to-day corrections into persistent memory and reusable skills for Claude Code. The talk covers the two-stage pipeline (hook-based capture + semantic validation), how learnings are queued for human review, and how patterns become new /commands via /reflect-skills.
I will walk through the architecture, tradeoffs in false-positive reduction, and a short live demo: correct the agent, run /reflect, and watch CLAUDE.md and skill files update.
Semantic AI system captures Claude Code corrections, generating permanent skill memory via CLAUDE.md.
- 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.
- Claude Code CLIAn agentic coding assistant that integrates Anthropic's AI models directly into your terminal for conversational development.Claude Code CLI is Anthropic's command-line interface (CLI) for agentic coding: it meets developers where they work, in the terminal. This tool allows you to build features from plain English descriptions, debug complex issues, and navigate any codebase with conversational commands. It is powerful because it takes action: the CLI can directly edit files, run shell commands, and even manage Git operations like creating commits and branches. Installation is straightforward via `npm install -g @anthropic-ai/claude-code`, and it's designed to be a flexible, scriptable power tool that automates tedious tasks like fixing linting errors or resolving merge conflicts.
- Claude Code skillsModular, self-contained packages that transform Claude into a specialized agent: they automate complex, multi-step workflows using proven instructions and code, dynamically loading only what is needed.Claude Code Skills are your solution for high-efficiency, specialized automation. They function as modular, self-contained packages (e.g., `SKILL.md` files) that encode domain expertise and organizational knowledge. Claude dynamically discovers and loads these resources based on context (progressive disclosure), which minimizes token usage and maximizes speed. This system allows you to execute complex, multi-step workflows—like full code review or PDF processing—with a single command, consistently applying best practices across all your projects. Skills specialize Claude: you create the expert workflow once; Claude applies it everywhere.
- Claude Code pluginsPackage and share custom Claude Code functionality: bundle slash commands, sub-agents, and hooks for reusable, versioned workflow extensions.Claude Code plugins are the standardized extension system for the Claude Code agentic terminal tool. They package custom functionality—like slash commands, sub-agents, hooks, and MCP servers—into reusable, versioned bundles. This architecture allows developers to standardize and share specific toolchains and project conventions across teams (e.g., a 'security-review' plugin). Plugins move beyond local configuration, enabling distribution through marketplaces and installation via the `/plugin` command for consistent, efficient workflows on any project.
- PythonPython: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .
- Claude Code skills & pluginsA command-line agent that executes complex engineering tasks by integrating terminal access, file editing, and custom toolsets.Claude Code operates as an agentic loop within your local development environment. It leverages a specialized skill system (MCP) to interact with your filesystem, execute git commands, and run test suites like Vitest or Pytest. By connecting to the Model Context Protocol, developers can extend Claude's capabilities with plugins for Jira, Slack, or custom database connectors. This setup allows the model to research codebases, fix bugs, and refactor architecture with direct write access and real-time terminal feedback.
Related projects
Making claude code write more reliable code
Seattle
Learn about ATX, a tool that integrates with Claude code to provide real-time feedback, improving code reliability and…
Development automation with Claude Code
Seattle
Learn about a practical Claude Code setup for development automation, including spec-driven development, TDD enforcement, automated Git workflows,…
Custom Self Improving Subagents with Claude Code
Seattle
See a live demo of self-improving Claude Code agents that learn, maintain expertise files, and share knowledge across…
Claude Code as Your Everything Agent: A Persistent, Self-Improving AI Workspace
Orange County
See a practical, hacky architecture for a persistent "everything agent" built on Claude Code, handling diverse tasks without…
Turning Claude Code into a Self-Improving Agentic Development Platform
Orange County
Learn how to turn AI coding sessions into a self-improving platform using reinforcement learning and verifiable rewards, training…
What Claude Code Should Be
San Diego