Agent Memory & State
Where do vector stores and RAG corpora sit relative to agent execution layers?
Vector stores and RAG corpora sit outside the core durable agent execution layer. These external systems store unstructured data for retrieval during agent runs, but do not track execution progress or need inclusion in replayable checkpoints. Agents call these stores during workflow steps to fetch relevant context as needed. Caveat: Track retrieval calls in workflow state if audit or replay requires visibility into fetched data.
Was this article helpful?
Your feedback helps improve Diagrid's FAQ experience.
Keep reading
More Diagrid FAQ articles
- Agent Memory & State
How do workflow state, conversation memory, and retrieval corpora differ for AI agents?
Explain how workflow state, conversation memory, and retrieval corpora differ for AI agents, including their unique roles in durable execution systems.
- Agent Memory & State
Which agent memory and state should be included in durable execution?
Outline which types of agent memory and state are appropriate for inclusion in durable execution layers for production AI agent workloads.
- Agent Memory & State
What agent state survives a workflow crash or restart?
Explain which agent state is preserved following a workflow crash or unexpected restart, and how Catalyst manages state persistence.