AI Series
Working with AI agents as a team of specialists: context, tooling, and where the human still decides.
9 parts
- 1
The human factor in the age of vibe-coding
AI accelerates your output but doesn't ensure quality. You're responsible for every line you commit. Speed without direction is chaos.
- 2
Why context is the real superpower
MCP connects AI agents to your dev tools, databases, and APIs through a standard protocol. Give your agent the context it actually needs.
- 3
From solo assistant to coordinated workforce
Stop using AI as a single assistant. Organize agents into specialized teams with roles, docs, and parallel execution for real leverage.
- 4
Holding both ends of the rope
Doing things right against getting things done. TDD, pair programming, AI: the best results hold both ends of the rope.
- 5
A tutorial through rules, skills, agents, hooks, and settings
A hands-on tour of Claude Code's project folder. What rules, skills, agents, hooks, and settings each do, and how they fit together.
- 6
From copy-paste prompts to agentic teams
A six-level ladder of AI adoption, from copy-paste prompts to agentic teams and AI-native workflows. Where most companies stall, and how to climb.
- 7
Intelligence without expertise is entertainment
Why Claude Code skills beat specialized agents. On-demand context, not the model, decides quality. Build a skill library that travels with your code.
- 8
Two leaks, two patches
Caveman shrinks what the agent says back, RTK shrinks what your terminal pipes in. More room in the same context window.
- 9
Attention is the one thing you can't scale
AI agents ship faster than you can review. The answer isn't speeding up. It's choosing where your attention actually matters.
