Runs

Runs execute one agent request without preserving chat history.

A run is a single execution of an agent. It takes an input, uses the agent's configured resources, and returns an output.

When To Use Runs

Runs are best for:

  • Classifying or summarizing one item.
  • Generating a response for a backend workflow.
  • Processing a form submission.
  • Testing an agent without creating a chat history.

Runs vs Threads

FeatureRunThread
Stores chat historyNoYes
Best forOne-off tasksMulti-turn chat
Typical endpoint/run/stream/threads
ReturnsFinal outputStreamed events and conversation state

Inputs

Runs can include a query, file URLs, context IDs, and metadata. Keep metadata structured and avoid sending secrets.