> 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/binary.md).

# Yes/No Questions

Ask a yes/no question with the experimental Decision API and read the probability of "yes".

{% 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 `AIBinaryDecisionQuestion` to ask a question that has a yes or no answer. The answer is an `AIBinaryDecisionAnswer`, which holds the probability that the answer is "yes". You choose the threshold that counts as "yes".

## Question Properties

| Property        | Type      | Required | Description                                                       |
| --------------- | --------- | -------- | ----------------------------------------------------------------- |
| `Instructions`  | `string`  | Yes      | The yes/no question to decide.                                    |
| `TrueCriteria`  | `string?` | No       | What counts as "yes", when the instructions alone are not enough. |
| `FalseCriteria` | `string?` | No       | What counts as "no", when the instructions alone are not enough.  |

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

| Member                           | Type     | Description                                                                  |
| -------------------------------- | -------- | ---------------------------------------------------------------------------- |
| `TrueProbability`                | `double` | The model's estimated probability that the answer is "yes", from 0.0 to 1.0. |
| `IsTrue(double threshold = 0.5)` | `bool`   | Returns `true` when `TrueProbability` is at least `threshold`.               |

A binary answer has no separate confidence value. `TrueProbability` already tells you how sure the model is.

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

## Example

The following service flags comments for review. It spells out what "yes" and "no" mean. It uses a low threshold, so a person also reviews comments the model is unsure about:

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

```csharp
#pragma warning disable UMBRACOAI_DECISION

using Umbraco.AI.Core.Decision;

namespace MyProject.Services;

public class CommentModeration
{
    private readonly IAIDecisionService _decisionService;

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

    public async Task<bool> NeedsReviewAsync(string comment, CancellationToken cancellationToken)
    {
        var response = await _decisionService.AskAsync(
            decision => decision.WithAlias("comment-moderation"),
            new AIBinaryDecisionQuestion
            {
                Instructions = "Is this comment spam?",
                TrueCriteria = "Promotional, a scam, or unrelated links",
                FalseCriteria = "A genuine comment from a reader"
            },
            comment,
            cancellationToken);

        // Review anything with at least a 30% chance of being spam
        return response.Answer.IsTrue(0.3);
    }
}
```

{% endcode %}

Raise the threshold to act only on highly likely answers. For example, `response.Answer.IsTrue(0.9)` only treats highly likely spam as spam. Read `TrueProbability` directly when you need the number itself, such as for sorting or logging.

## Related

* [Decision](/ai-in-umbraco/19.latest/using-the-api/decision.md) - Overview, enabling, and profile selection
* [Pick-One Questions](/ai-in-umbraco/19.latest/using-the-api/decision/choice.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/binary.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.