> For the complete documentation index, see [llms.txt](https://docs.umbraco.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.umbraco.com/ai-in-umbraco/19.latest/using-the-api/decision/choice.md).

# Pick-One Questions

Ask the experimental Decision API to pick one of a fixed set of options and read the chosen key.

{% hint style="warning" %}
Decision is experimental and disabled by default. See [Enabling Decision](/ai-in-umbraco/19.latest/using-the-api/decision.md#enabling-decision).
{% endhint %}

Use `AIChoiceDecisionQuestion` to have the model pick one option from a fixed list. The answer is an `AIChoiceDecisionAnswer`, which returns the key of the chosen option.

## Question Properties

| Property       | Type                              | Required | Description                                            |
| -------------- | --------------------------------- | -------- | ------------------------------------------------------ |
| `Instructions` | `string`                          | Yes      | What to decide.                                        |
| `Options`      | `IReadOnlyList<AIDecisionOption>` | Yes      | The options to choose from. Between 2 and 255 entries. |

Each `AIDecisionOption` has a `Key` and an optional `Description`:

{% code title="AIDecisionOption.cs" %}

```csharp
public sealed record AIDecisionOption(string Key, string? Description = null);
```

{% endcode %}

* `Key` is the value returned when the option is chosen. Keys must be unique and not empty. Keys are compared exactly, including case.
* `Description` explains what the key means. Add one when the key alone is not clear, such as an ID.

Pass the content to judge as the `state` argument of `AskAsync`, or as the request's `State`. Questions also have an optional `Id`. See [Requests, Questions, and Answers](/ai-in-umbraco/19.latest/using-the-api/decision.md#requests-questions-and-answers).

## Answer Properties

| Property        | Type                                  | Description                                                                                                                                                   |
| --------------- | ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `Choice`        | `string`                              | The `Key` of the chosen option, exactly as you supplied it.                                                                                                   |
| `Probabilities` | `IReadOnlyDictionary<string, double>` | The estimated probability for every option, keyed by option key. The probabilities add up to 1.                                                               |
| `Confidence`    | `double?`                             | The provider's own confidence in `Choice`, from 0.0 to 1.0. `null` when the provider does not report one. Values from different providers are not comparable. |

`AskAsync` returns an `AIDecisionResponse<AIChoiceDecisionAnswer>`. Read the answer from its `Answer` property. The response also has `ModelId` and `Usage`.

## Example

The following service routes a support message to a team:

{% code title="SupportRouter.cs" %}

```csharp
#pragma warning disable UMBRACOAI_DECISION

using Umbraco.AI.Core.Decision;

namespace MyProject.Services;

public class SupportRouter
{
    private readonly IAIDecisionService _decisionService;

    public SupportRouter(IAIDecisionService decisionService)
    {
        _decisionService = decisionService;
    }

    public async Task<string> RouteAsync(string message, CancellationToken cancellationToken)
    {
        var response = await _decisionService.AskAsync(
            decision => decision.WithAlias("support-routing"),
            new AIChoiceDecisionQuestion
            {
                Instructions = "Which team should handle this message?",
                Options =
                [
                    new AIDecisionOption("billing", "Invoices, payments, and refunds"),
                    new AIDecisionOption("technical", "Errors, bugs, and how-to questions"),
                    new AIDecisionOption("sales", "Pricing and new purchases")
                ]
            },
            message,
            cancellationToken);

        return response.Answer.Choice; // "billing", "technical", or "sales"
    }
}
```

{% endcode %}

## Related

* [Decision](/ai-in-umbraco/19.latest/using-the-api/decision.md) - Overview, enabling, and profile selection
* [Yes/No Questions](/ai-in-umbraco/19.latest/using-the-api/decision/binary.md)
* [Score Questions](/ai-in-umbraco/19.latest/using-the-api/decision/score.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.umbraco.com/ai-in-umbraco/19.latest/using-the-api/decision/choice.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.