What is a Token?
•2 min read
Definition and explanation of tokens in large language models.
Model Context Protocol: Connecting AI to Your Tools
•3 min read
MCP provides a standardized way for AIs to interact with tools, from Figma to your calendar to custom workflows you build yourself.
Prompting Techniques That Actually Work
•5 min read
Five prompting techniques that improve LLM outputs: few-shot learning, chain-of-thought reasoning, XML structure, output constraints, and prompt chaining.
How Prompt Priming Shapes LLM Responses
•3 min read
Your prompt's opening sets the context for the entire response.
How LLMs Think and Respond
•3 min read
LLMs generate text one token at a time. Understanding how they convert text to vectors, use attention to weigh context, and predict probabilities explains their behavior.
Debugging LLMs: Understanding Attention, Tokens, and Context
•3 min read
When models fail or behave unexpectedly, you need to understand why. Practical debugging techniques for tokenization, attention patterns, and context limits.
Progressive Disclosure in Agent Skills
•1 min read
The architectural pattern that makes Agent Skills scalable: load only what's needed, when it's needed.
Building Agent Skills: A Practical Guide
•4 min read
Anthropic's Agent Skills let you equip Claude with specialized capabilities through reusable skill packages. Here's how to build them.