Choose the right LLM for the job
A practical guide to choosing fast, general, reasoning, long-context, multimodal and specialist models by workflow phase.
Topic
workflows
Practical notes to help you make the next useful move.
← Back to the library
Herdr: one terminal for the whole herd
A practical first look at Herdr, a terminal-native multiplexer for keeping coding agents, shells and long-running work together.
Spend tokens on decisions, not noise
A practical look at the four tools I use to keep AI coding sessions focused: Caveman, Ponytail, RTK and Graphify.
Agent brief template: give the work a finish line
A copyable brief for giving an agent a clear goal, useful context, and a definition of done.
Watch: Agentic AI — workflows vs. agents
A short visual explainer for choosing a fixed workflow, an agent, or a combination of both.
Agents and skills: what is the difference?
A practical mental model for deciding when you need an agent, a skill, or both.
Turn a repeated task into an AI skill
Build a small, testable skill from work you already repeat instead of starting every request from scratch.