A working handbook for operating AI systems.

Harnesses, agents, MCP, multi-agent workflows — taught through patterns you can paste and run, not theory. Every lesson ends with an asset you can use on your own task. No account needed to read.

Start with a lesson Browse Foundations

FoundationsAn ordered concept spine, beginner to advanced — using AI, agents, orchestration, context.Start here if you are getting from “I know it’s powerful” to a first real win.DomainsApplied go-to-market playbooks — sales, marketing, content, growth, BD.For specialists who want an AI-native motion in their own pipeline, not generic advice.ToolkitPractical assets you can grab without reading a lesson — MCPs, prompts, templates, people.For the returning reader who wants the asset, not the explanation.

Start here

41 lessons and counting

Context Engineering: Curating the Window
After this you can run the context window as a curated working set.
IntermediateFoundations
Prompting Fundamentals That Actually Move Output
After this you can take a prompt that is giving you mediocre results and improve it on the next try by being more specific and cutting what does not earn its place, rather than piling on more instructions and examples and hoping.
BeginnerFoundations
The Agent Loop: From Answering to Acting
After this you can tell when a task actually needs an agent, build the loop around the model rather than expecting the model to be the agent, and stop the loop before it runs away.
IntermediateFoundations
Multi-Agent Orchestration: When One Isn't Enough
After this you can judge whether a task actually benefits from multiple agents, fan it out without the results collapsing into incoherence, and recognize that synthesis, not spawning, is where the real work lives.
AdvancedFoundations

A working handbook for operating AI systems.

Start here

Context Engineering: Curating the Window

Prompting Fundamentals That Actually Move Output

The Agent Loop: From Answering to Acting

Multi-Agent Orchestration: When One Isn't Enough