Glossary
Context engineering
What is context engineering?
Context engineering is deciding what information an AI model sees for each task, such as instructions, examples, documents and tool results, so it has what it needs and nothing that distracts it.
Why it matters
Many agent errors come from missing or wrong context rather than a weak model. Good context often matters more than picking a bigger model.
Example
A support agent gets the ticket, the customer’s plan, the three most relevant help articles and the routing rules, not the entire help center.
Learn more
Guide · DecideHow to choose an AI model by cost per taskMeasure cost per task, not price per token, and find where a cheaper model does the same job.Guide · EquipWhat is an AI agent harness? The software that turns a model into an agentThe software that turns a model into an agent: what it does, why it matters, and what to ask vendors about theirs.Guide · SeeWhat is agent experience (AX)? How to make your company navigable for AI agentsWhat AX means, why AI agents get lost inside companies, and how to give them what a new hire gets.