Skip to main content
Intelligence controls the language model behind an agent’s responses. It is one of the configuration tabs in Agent Studio, alongside the instructions in Agent Core.

​
Choose a model

Open an agent, select Intelligence, and choose a model under Language Model. The model is used by the live voice pipeline and by the agent’s browser and test experiences. The available options are validated server-side, so a model shown as coming soon cannot be activated by editing the request or configuration directly.
Model availability may vary by workspace. Choose from the models enabled in your Agent Studio.

​
Tune response parameters

​
Temperature

Temperature controls how much variation the model can use when producing a response. The Studio accepts a value from 0 to 2 and starts new agents at 0.4.
  • Lower values make the agent more focused and repeatable.
  • Higher values allow more creative variation, but can make a tightly scripted agent less consistent.
For customer support, booking, qualification, or policy flows, start low and raise the value only when the agent sounds too rigid. Temperature does not replace clear instructions in Agent Core.

​
Max Tokens

Max Tokens sets the maximum response length for one model turn. The Studio accepts values from 64 to 4096 and uses 256 by default. Keep this limit aligned with the channel:
  • Phone agents usually work best with short replies and a modest limit.
  • An agent that needs to explain several options may need a larger limit.
  • A larger limit does not require the agent to use all of it; your prompt should still say how concise the response should be.
When tools are enabled, allow enough response space for the agent to complete an action. This does not mean the agent needs to speak a long answer to the caller.

​
A practical starting point

  1. Start with GPT-4o Mini, Temperature 0.4, and Max Tokens 256.
  2. Make the response style in Agent Core explicit: keep phone replies short, ask one question at a time, and do not invent facts.
  3. Test the same path in Chat, Talk, or Call.
  4. Move to GPT-5.4 Mini when responsiveness is the priority, or GPT-4o when a tested flow needs more reasoning.

​
Save and verify

Select Save Changes after changing the model or parameters. Then test a representative path:
  • Ask a straightforward question to check latency and tone.
  • Give the agent an ambiguous request to check whether it asks for clarification.
  • If the agent has tools, test both a successful action and a failed action.
Intelligence affects generation. The agent’s role, rules, language behavior, and conversation order still come from Agent Core, while live-call timing and handoff behavior are configured in Runtime.