> For the complete documentation index, see [llms.txt](https://cc.docs.landis.cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://cc.docs.landis.cloud/setup/setup-ai-interaction-summary.md).

# Setup AI Interaction Summary

**This feature is in** [**Preview**](/appendix/feature-states.md)**.**

This feature allows administrators to configure a custom AI prompt that is automatically executed when a call or chat is completed. The prompt can incorporate call transcription data and other available call details to generate an AI response. The generated response is displayed in the same locations as the call transcription within Quality Management and Interaction Details.

1. Set up policy call recording for each user. See [Set Up Policy Call Recording](/setup/setup-policy-call-recording.md)
2. [Set Up Transcription and Sentiment Analysis](/setup/set-up-sentiment-analysis.md)
3. Create enterprise application in Azure: Navigate to Landis Contact Center | Administration | Settings | General Tab | Select the Grant Permissions button for Create enterprise application for Contact Center to interact with Microsoft Foundry
4. Create or select an existing Azure Foundry Agent or Azure chat completion model to process the prompt requests.
5. In the Azure Foundry resource, assign the Foundry User role to the Landis Contact Center - AI Services service principal.
6. Configure a connection to an Azure Foundry Agent or Azure chat completion model

{% tabs %}
{% tab title="Azure Foundry Agent" %}

1. [https://ai.azure.com](https://ai.azure.com/) | Select the project on the top left corner | Copy the project endpoint
2. Landis Contact Center | Administration | AI Connections | Add
3. Enter a name for the AI Connection. Description field is optional.
4. Change the Type to Foundry Agent
5. Paste the project endpoint into the Endpoint field
6. Select the Agent Name and Agent Version from the dropdown. The information in the dropdown should populate automatically if the appropriate permissions were granted.
7. Save
   {% endtab %}

{% tab title="Azure Chat Completion model" %}

1. [https://ai.azure.com](https://ai.azure.com/) | Disable "New Foundry" on the top of the page | Select the project on the top left corner | Overview | Under the Libraries heading, select Azure AI Services | Copy the Azure AI Services endpoint

2.  [https://ai.azure.com](https://ai.azure.com/) | Models + endpoints | Copy the deployment name

3. Landis Contact Center | Administration | AI Connections | Add

4. Enter a name for the AI Connection. Description field is optional.

5. Change the Type to Chat Completions

6. Paste the Azure AI Services endpoint into the Endpoint field from step 1

7. Paste the deployment name from step 2

8. Save
   {% endtab %}
   {% endtabs %}

9. Create Interaction Transformations (AI Prompts). Navigate to Configuration | Interaction Transformations | Add. Enter a name for the Interaction Transformation and create a prompt. Select the AI Connection that was created in step 6. Example Prompt: Summarize this call/chat in 2-3 sentences. Call/chat transcription: {calltranscription}

{% hint style="info" %}
All available placeholders can be viewed and then selected by entering {.
{% endhint %}

8. Assign the Interaction Transformations to queues or direct call records groups

{% tabs %}
{% tab title="Queue" %}
Queues & IVRs | Queues | Edit queue | Integrations tab | In the Interaction Transformation dropdown, select the Interaction Transformation that was created in step 7.
{% endtab %}

{% tab title="Direct Call Record Group" %}
Configuration | Direct Call Records Groups | Edit Direct Call Records Group | In the Interaction Transformation dropdown, select the Interaction Transformation that was created in step 7.
{% endtab %}
{% endtabs %}

9. The prompt response should show on any new calls or chats to the queue or direct call record group. You can view the prompt response where the transcription is diplayed in the Quality Management panel or Interaction details report.


---

# 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://cc.docs.landis.cloud/setup/setup-ai-interaction-summary.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.