VOLUME 01 // GLOSSARY
AI agent and prompt engineering glossary
The terms that keep showing up in our news desk, defined in plain language: what each one means, where it comes from, how it fails in practice, and what to change in your prompts or your agent because of it.
Glossary
Agent memory
Agent memory is the information an AI agent stores outside its context window, in files, databases, or indexes, and reads back later so it can remember across steps and sessions.
Updated
Glossary
Context compaction
Context compaction is when an AI agent nears its context window limit and replaces older conversation turns with a model-written summary so the session can keep going.
Updated
Glossary
Prompt injection
Prompt injection is an attack where text the model reads as data, such as a web page, email, or file, contains instructions that the model follows as if they came from you.
Updated
Glossary
RSI (recursive self-improvement)
RSI, or recursive self-improvement, is when an AI system helps build a better version of itself, and that better version is in turn better at building the next one.
Updated