AI engineering glossary · Agents tools MCP
What is memory retrieval?
Memory retrieval: Finding the stored memories that matter for the current step, typically by embedding the current situation and searching for the closest stored items, sometimes weighed by recency and importance. Poor retrieval means the agent forgets or is distracted by irrelevant notes.
Memory retrieval: an example
Before replying, the agent searches memory for 'refund policy' and pulls the three closest notes into the prompt.
Related terms
More Agents tools MCP terms
- Model Context Protocol
- Model routing
- Multi-agent system
- OpenAI Agents SDK
- Orchestrator-worker pattern
- Parallelisation pattern
- Plan-and-execute
- Planning (agents)
Where you learn it
Memory retrieval is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.