Reasoning and quality

Two sets of controls shape how good your answers are: the model tier and reasoning you pick per agent, and the optional conversation analysis that grades finished chats after the fact.

Base and Premium

On most plans you choose a quality tier rather than a raw model:

• Base — fast and economical, the right default for most assistants.
• Premium — a stronger model for harder questions. A Premium reply draws more from your monthly message-credit allowance than a Base reply.

On the BYOK and Custom plans you instead pick the exact model and sampling settings yourself. You set the tier per agent on the agent form — see Agents.

Extended thinking

Some models can "think" through a problem before answering. Where a tier supports it, the agent form shows an "extended thinking" hint, and you can enable reasoning for that agent.

You also decide whether visitors see the thinking. With Show reasoning to visitors on, the widget shows a collapsible "Thinking…" panel that streams while the answer is being worked out. With it off, the chain of thought is hidden from visitors but still kept for your own review in the conversation diagnostics.

Conversation analysis

Turning on Analyze conversations for an agent has the platform review finished chats in the background and grade them:

• a helpfulness verdict — helpful, partial, or unhelpful;
• a knowledge gap flag with a short summary, when the assistant couldn't answer because the material wasn't in its library.

These signals surface in the Quality section of the dashboard, where a knowledge gap is your cue to add the missing answer as a library source. Each review draws a small amount from your monthly allowance, shown on the agent form when you switch it on.

See Conversation analysis for the Quality section in full, and Libraries and sources to close a gap.

See also: Agents and Conversation analysis.