Beyond Chatbots: Build Your Personal AI Operating System

Chatbot webapps are great for one-off questions — but they're not where the real power lives. In this session, we'll move into local agentic tools and learn how to assemble a personalized AI "operating system" built around your workflow. Whether you're shipping code, managing products, recruiting, or running a solo business, the building blocks are the same.

What We'll Cover

1. CLAUDE.md & Project Context

How agents read project-level instructions to understand your world. Think of it as writing an onboarding doc for your AI — the better the context, the less you repeat yourself.

2. Skills

Reusable capabilities your agent can invoke on demand. Instead of re-explaining a task every time, you define it once as a skill and call it whenever you need it.

3. Subagents

Delegating specialized tasks to focused child agents — your "AI employees." Each one can handle a different part of a complex workflow, working in parallel or in sequence.

4. MCP (Model Context Protocol)

The protocol for connecting agents to external tools, APIs, and data sources. MCP is what turns a chatbot into something that can actually do things in the real world.

5. Agent Teams

Orchestrating multiple agents for complex, multi-step workflows. When one agent isn't enough, you coordinate a team — each with its own role, tools, and context.

6. Plugins & Plugin Registries

The emerging ecosystem of agent extensions and marketplaces. Browse, install, and share capabilities — so you don't have to build everything from scratch.

7. Claude + Cursor Workflow

Using Claude for planning and architecture, and Cursor Composer for fast code execution. Get the best of both worlds: deep thinking paired with rapid implementation.

Key Takeaway

These concepts aren't tied to any single tool. Skills, subagents, MCP, and agent teams are becoming the standard building blocks across all agentic IDEs and coding agents. Learn them once, apply them everywhere.