> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vocily.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Intelligence

> Choose the language model and tune how your agent generates responses.

**Intelligence** controls the language model behind an agent's responses. It is one of the
configuration tabs in [Agent Studio](/building-agents/overview), alongside the instructions in
[Agent Core](/building-agents/agent-core).

## Choose a model

Open an agent, select **Intelligence**, and choose a model under **Language Model**.

| Model             | Best for                                                | Current state                                              |
| ----------------- | ------------------------------------------------------- | ---------------------------------------------------------- |
| **GPT-4o Mini**   | A balanced default for most agents                      | Recommended                                                |
| **GPT-5.4 Mini**  | Lower-latency responses                                 | Available                                                  |
| **GPT-4o**        | More complex reasoning when extra latency is acceptable | Available                                                  |
| **Claude Sonnet** | —                                                       | Shown as coming soon and unavailable in the current Studio |

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.

<Note>
  Model availability may vary by workspace. Choose from the models enabled in your Agent
  Studio.
</Note>

## 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](/test/overview).
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](/building-agents/agent-core), while live-call timing and
handoff behavior are configured in [Runtime](/building-agents/runtime).