Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Claude Code: Self-Improving Agent Architecture
See a live demo of self-improving Claude Code agents that learn, maintain expertise files, and share knowledge across domains for continuous improvement.
Most Claude Code setups are static—your agents do the same thing every time. But what if they could learn from their own execution?
In this talk, I’ll demo a self-improving subagent architecture running in Claude Code that uses a plan→build→improve cycle where agents update their own knowledge after every workflow, maintains expertise.yaml files (500-1000 lines per domain) that evolve based on real execution patterns, and shares learnings across domains via a collective knowledge registry so when one agent discovers something, all agents can benefit.
Live demo: I’ll show agents improving themselves in real-time, including the .shared/ folder pattern for cross-domain knowledge propagation.
- 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 OpusClaude Opus: Anthropic's flagship large language model, delivering frontier intelligence for complex reasoning, advanced coding, and autonomous agentic workflows.Claude Opus is Anthropic's most capable foundation model (LLM), setting the industry benchmark for complex reasoning, math, and coding. It achieves state-of-the-art results on key evaluations: Opus 4.1 scored 74.5% on SWE-bench Verified. The model features a massive 200,000-token context window (expandable to 1 million for specialized tasks), enabling deep, multi-file analysis and long-horizon agentic workflows. Deploy Opus for enterprise-grade automation, complex financial forecasting, or expediting R&D across critical sectors.
- SonnetSonnet is Anthropic's powerful, mid-tier AI model, balancing frontier intelligence with high-speed, cost-efficient performance for production-scale deployments.Sonnet (currently Claude Sonnet 4.5) is Anthropic’s versatile model, optimized for complex agentic workflows and coding tasks. It delivers state-of-the-art performance, achieving 77.2% on the SWE-bench Verified coding benchmark (cite: 2.2, 2.4). The model is engineered for high-volume, real-time applications like customer support automation and financial analysis, supporting a 200K token context window (cite: 2.8). Pricing is set for efficiency: $3 per million input tokens (cite: 2.8). This makes Sonnet the recommended choice for developers needing top-tier reasoning and coding capability at a practical, scalable cost.
- HaikuHaiku is a fast, open-source operating system, a community-driven continuation of the BeOS platform, specifically targeting efficient personal computing.Haiku, originally OpenBeOS, is a free, open-source operating system that directly succeeds the BeOS architecture; development began in 2001. The system is built for responsiveness, featuring a fully threaded design for maximum efficiency on multi-core CPUs and a custom hybrid kernel derived from NewOS. It utilizes the Be File System (BFS), which supports indexed metadata, treating the file system like a database. The entire project (kernel, drivers, toolkit, and desktop applications) is written by a single team, ensuring a unique level of consistency and a cohesive object-oriented API for accelerated C++ development.
- YAMLYAML (YAML Ain't Markup Language) is a human-friendly data serialization language prioritizing readability and ease of use.YAML is a human-readable data serialization language, primarily used for configuration files and inter-process data exchange. It employs a minimal, indentation-based syntax (like Python) to define structure, utilizing colons for key-value pairs (mappings) and hyphens for list items (sequences). YAML is a superset of JSON, offering key benefits like support for comments and reusable data references (anchors). This clarity and feature set make it the standard for major DevOps tools, including Kubernetes deployments and Ansible Playbooks.