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

# Configuration

> Common Portal configuration patterns (application / intent / intent group)

Maitai’s Portal exposes a **Configuration** panel at multiple scopes so you can tune behavior without shipping code changes.

## Where to configure

In the Portal, configuration appears in these places:

* **Application**: `/application/:applicationId`, then **Configuration**
* **Intent Group**: `/intent-group/:intentGroupId`, then **Configuration**
* **Intent (ApplicationAction)**: `/application/:applicationId/intent/:actionId`, then **Configuration**
* **Test Run**: the Test Run wizard includes a configuration step used for that run

<img src="https://mintcdn.com/maitai-cbe2cd27/kcIewhDoyU5XOGPZ/images/portal_application_intent_config.png?fit=max&auto=format&n=kcIewhDoyU5XOGPZ&q=85&s=793cc21fb67f42ea11cc3984a882cd21" alt="config portal" width="1685" height="1295" data-path="images/portal_application_intent_config.png" />

## Common patterns

### Enable evaluations + corrections

* Turn on **Evaluations**
* Optionally turn on **Apply Corrections**
  * This toggle is only available when evaluations are enabled.
  * Enabling corrections unlocks **Safe Mode**.

### Add a secondary model + fallback behavior

* Select a **Secondary Model**
* Choose a **Fallback Strategy**
* Optionally set a **Fallback Timeout** (only appears for timeout strategy)

### Make output more deterministic

* Lower **Temperature**
* Use a **Stop Sequence**
* Set **Max Tokens**

## Parameters available in the Portal Configuration panel

<ParamField path="Inference Location" type="Client or Server">
  Controls where inference is executed.
</ParamField>

<ParamField path="Reasoning Effort" type="string">
  Controls the model’s reasoning depth when supported by the selected model.
</ParamField>

<ParamField path="Evaluations" type="boolean" default={true}>
  Enables Sentinel evaluation for requests at this scope.
</ParamField>

<ParamField path="Apply Corrections" type="boolean" default={false}>
  <Warning>Corrections are only available for Server inference, and require Evaluations to be turned on.</Warning>

  Enables automatic correction behavior when evaluations identify faults.
</ParamField>

<ParamField path="Safe Mode" type="boolean" default={false}>
  Safe mode prioritizes accuracy over latency. Only available when Apply Corrections is enabled.
</ParamField>

<ParamField path="Model" type="string">
  Primary AI model to be used for inference. Models are grouped by provider and sorted alphabetically, with Maitai models (recommended) appearing first.
</ParamField>

<ParamField path="Secondary Model" type="string">
  Optional fallback model to use if the primary model is not available or has degraded performance.
</ParamField>

<ParamField path="Fallback Strategy" type="string" default="reactive">
  Strategy to use when falling back to secondary model. Options:

  * `reactive`: Falls back on primary model failure
    * If a timeout is specified, it will initiate the fallback request after the timeout period
  * `timeout`: Falls back after specified timeout period
  * `first_response`: Uses whichever model responds first
    * If a timeout is specified, it will only use the fallback model after the timeout period
</ParamField>

<ParamField path="Fallback Timeout" type="number">
  Timeout in seconds before falling back to secondary model. Only applicable when using the "timeout" fallback strategy.
</ParamField>

<ParamField path="Temperature" type="number" default={1}>
  Controls randomness in the model's output. Range 0-2, where:

  * Lower values (e.g., 0): More deterministic output
  * Higher values (e.g., 2): More random output
</ParamField>

<ParamField path="Stop Sequence" type="string">
  Sequences where the API will stop generating further tokens.
</ParamField>

<ParamField path="Log Probs" type="boolean" default={false}>
  Include the log probabilities of the output tokens.
</ParamField>

<ParamField path="N" type="integer" default={1}>
  How many completions to generate for each prompt.
</ParamField>

<ParamField path="Max Tokens" type="integer">
  The maximum number of tokens to generate in the completion.
</ParamField>

<ParamField path="Presence Penalty" type="number" default={0}>
  Range -2 to 2. Increases the model's likelihood to talk about new topics.
</ParamField>

<ParamField path="Frequency Penalty" type="number" default={0}>
  Range -2 to 2. Decreases the model's likelihood to repeat the same line verbatim.
</ParamField>