Quick and Deep modes
Quick
A fast, single-pass path for direct questions. It retrieves relevant knowledge-base content and returns an answer with minimal orchestration.
Deep
A multi-step agent loop for questions that need repeated searches, connected data, charts, apps, tools, or delegation.
quick or deep with the agent_mode request field.
The Deep agent loop
Plan
The model interprets the message, available context, and tool catalog, then chooses the next useful action.
Call a tool
It can search the knowledge base, run read-only SQL, build a chart, call a connected app or custom tool, use an MCP server, or delegate to another agent.
Observe
Tool results return to the model as grounded context. The model can refine its plan and call another tool when needed.
Runtime capabilities
| Capability | Quick | Deep |
|---|---|---|
| Knowledge-base retrieval | Single-pass | Repeated, agent-directed searches |
| Source citations | When retrieval finds supporting passages | When retrieval finds supporting passages |
| Read-only connected database queries | — | Yes |
| Charts from connected data | — | Yes |
| Connected apps and custom tools | — | Yes |
| MCP tools | — | Yes |
| Agent delegation | — | Yes |
The exact tools available in a Deep run depend on the knowledge base, chat, or agent configuration and the caller’s access. Connected apps must be authenticated before the runtime can use them.
Streaming a run
Streaming endpoints expose the run as it happens. Events can include progress, tool activity, final-response content, sources, charts, token usage, completion, and errors. The main runtime normally emits one canonicalfinal_response with isComplete: true; clients should also support partial final_response events and accumulate their content for protocol compatibility.
The non-streaming endpoints use the same runtime and return after the final result is ready. See Chat lifecycle and Chat & streaming for request and event details.
Grounding and context
The runtime does not place the entire document corpus into the prompt. Instead, it receives a short preview of available content, searches at run time, and adds the retrieved passages as tool results. Conversation summaries and durable memory are separate context layers. Read Prompt assembly for precedence and RAG lifecycle for retrieval behavior.Next steps
Prompt assembly
Understand prompt layers, memory, history, and custom overrides.
RAG lifecycle
Follow a knowledge-base search from query to cited source.