← Back to home
Explainers
One AI concept, explained for the decision
Short reference pieces. Each one explains a single Gen AI concept, shows how it works in one diagram, and ends with the questions to ask your team.
-
Harness: The Software That Turns a Model's Answers Into Work
A harness is the software that manages how an AI model works: what it sees, the tools it can use and its limits. It's why one model can do different work.
Read the explainer → -
Context Window: The Token Limit for One AI Model Call
A context window is the most tokens a model can handle in one call, input and output together. What fills it, and why fitting isn't enough.
Read the explainer → -
System Prompt: The Instructions an App Gives an AI Model
A system prompt is the instructions and background an app gives an AI model, separately from your messages. What it holds, how it works, who owns it.
Read the explainer → -
Tokens: The Chunks of Text an AI Model Reads and Writes
A token is a chunk of text an AI model reads and writes as one unit. How text becomes tokens, why counts vary, and how to compare model prices.
Read the explainer →