AI Series
Working with AI agents as a team of specialists: context, tooling, and where the human still decides.
8 parts
- 1
AI Gives You Speed, Not Quality
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
MCP: Giving Your AI Agent the Right Context
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
Build Your Own Team of Agents
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
Idealism vs Pragmatism
Holding both ends of the rope
The tension between doing things right and getting things done shapes every decision in software and in life. TDD, pair programming, AI adoption: the best results come from holding both ends of the rope.
- 5
Inside the .claude Folder
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
The Levels of AI Adoption
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
Skills Over Agents
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
Cut the Token Bill on Both Ends
Two leaks, two patches
Two small tools that compound: Caveman shrinks what the agent says back, RTK shrinks what your terminal pipes in. More room in the same context window, same model, same prompts.