> For the complete documentation index, see [llms.txt](https://docs.opendialog.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.opendialog.ai/getting-started-1/quick-start-ai-agents/the-start-from-scratch-ai-agent/global-no-match-conversation.md).

# Global No Match Conversation

The No Match Conversation provides the top level point where a No Match can be deal with.

A No Match is "issued" by the OpenDialog Engine when no interpreted has found a matching intent at a certain context level.

Keep in mind that the Topics conversation has its own No Match scene.

<figure><img src="/files/LV0ZMjZS5OfxFONK35Cz" alt=""><figcaption></figcaption></figure>

When the No Match intent is matched 😉 we reply with a NoMatchResponse that uses an LLM Action - the No Match Response Generation action to generate an appropriate message.

Immediately afterwards we issue the `intent.core.restart` intent as a [virtual intent.](/opendialog-platform/conversation-designer/message-design/subsequent-messages-virtual-intents.md) This will enable us to force a restart of the conversation.

<figure><img src="/files/pv6kf87Lw7e7hGqfokvY" alt=""><figcaption><p>The No Match turn with a virtual intent</p></figcaption></figure>

{% hint style="info" %}
Forcing a restart of the conversation after a Global No Match can often make sense since it means that we've failed to interpret what the user said at all previous levels. It is adviced to avoid hiting the Global No Match as much as possible and instead introduce local No Match intents at various scenes as appropriate.
{% endhint %}


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.opendialog.ai/getting-started-1/quick-start-ai-agents/the-start-from-scratch-ai-agent/global-no-match-conversation.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.