← The Modern AI Developer
Letting AI Actually Do Things: AI IDEs & Tooling
In the first two levels the Agent could only 'think.' This level lets it actually act: working in an AI IDE (Cursor / Claude Code) on your project, learning the sync and async ways to collaborate, how to let go, and how to keep long context from derailing it. Then on to code-gen patterns—designing good tools for it, using CLAUDE.md to make it remember the project's rules, turning personal tricks into team conventions, and finally plugging in MCP to add a whole row of external capabilities at once.
Unit 1
Into the AI IDE
Bring the Agent into your code editor: learn to watch it work, hand work off to it, and hit the brakes before it derails on you.
- 1Getting Started with AI Coding ToolsWhat exactly do Cursor / Claude Code add over a normal editor6 Q
- 2Sync vs. Async AgentsWatch it work step by step, or send it off to run to completion and report back6 Q
- 3Semi-Async Workflows: How Far to Let GoWhich tasks you can hand off, which you must watch6 Q
- 4Why Long Context DerailsFeed it too much and it forgets and drifts—how to defend against it6 Q
Unit 2
Code-Generation Patterns
Turn the Agent into a handy partner: give it good tools, make it remember the project's rules, distill your experience into team conventions, and plug in MCP to expand its abilities in one move.
- 1How to Design Good Tools for an AgentSmall and clear, single responsibility, well described6 Q
- 2The CLAUDE.md Pattern: Make It Remember the Project's RulesProject-level long-term memory / convention file6 Q
- 3How Teams Share AI KnowledgeDistill personal tricks into reusable team conventions6 Q
- 4Connecting MCP: Plug a Whole Row of External Abilities into the AgentMCP in plain words: a standard plug—connect once, get a row of tools6 Q