This page shows you how to set up Agent Assist for
Contact Center AI Platform (CCAI Platform). Agent Assist provides in-the-moment assistance
to your human agents, helping them resolve customer issues faster and with
greater accuracy.

## Set up Agent Assist

This section shows you how to set up Agent Assist.

### Service account requirements

To use Agent Assist, you need to [create a
Google Cloud Service Account and key](https://docs.cloud.google.com/contact-center/ccai-platform/docs/virtual-agent#create-a-service-account-and-key) in
the project where you [created your Agent Assist conversation
profile](https://docs.cloud.google.com/contact-center/ccai-platform/docs/virtual-agent#create-cp). In addition, you must grant the following
IAM roles to your service account:

- [Dialogflow Agent Assist
  Client](https://docs.cloud.google.com/iam/docs/roles-permissions/dialogflow#dialogflow.agentAssistClient)

- [Dialogflow API Admin](https://docs.cloud.google.com/iam/docs/roles-permissions/dialogflow#dialogflow.admin)

- [Data Labeling Service Admin](https://docs.cloud.google.com/iam/docs/roles-permissions/datalabeling#datalabeling.admin)

> [!NOTE]
> **Note:** Failure to grant the correct IAM role prevents Agent Assist from working correctly.

> [!CAUTION]
> **Caution:** Follow Google's [best practices for managing service account
> keys](https://docs.cloud.google.com/iam/docs/best-practices-for-managing-service-account-keys).

### Add an Agent Assist platform

To add an Agent Assist platform, follow these steps:

1. In the CCAI Platform portal, click **Settings \> Developer Settings** .
   If you don't see the **Settings** menu, click **Menu**.

2. Go to the **Agent Assist Platform** pane, and then click **Add platform** .
   The **Add an Agent Assist platform** dialog appears.

3. In the **Name** field, enter a name for your platform.

4. In the **Service** field, select **CCAI Conversation Profile** , and then
   click **Create**.

5. Click **Upload key** to upload your JSON service account key. For more
   information, see [Service account
   requirements](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#service-account-requirements).

6. Click **Close** to close the
   dialog.

### Configure Agent Assist for calls globally

You can use Agent Assist capabilities in the agent desktop or the call
adapter, but not both.

To configure Agent Assist for calls globally, follow these steps:

1. In the CCAI Platform portal, click **Settings \> Call** . If you don't
   see the **Settings** menu, click
   **Menu**.

2. Go to the **Agent Assist** pane, and then click the **Agent Assist** toggle
   to the on position.

3. In the **Knowledge \& Guidance** section, select one of the following
   options:

   - **Agent Assist Hub** . Select this option to use knowledge assist, agent
     coaching, and conversation summarization in the [**Agent Assist
     Hub**](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist-hub) panel of the agent desktop.

   - **Generative Knowledge Assist**. Select this option to use generative
     knowledge assist in the call adapter.

4. In the **Conversation Insights** section, select the [Agent Assist
   capabilities](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#aa-for-voice-calls) that you want, and then click **Save
   Agent Assist**.

### Configure Agent Assist for chats globally

You can use Agent Assist capabilities in the agent desktop or the chat
adapter, but not both.

To configure Agent Assist for chats globally, follow these steps:

1. In the CCAI Platform portal, click **Settings \> Chat** . If you don't
   see the **Settings** menu, click
   **Menu**.

2. Go to the **Agent Assist** pane, and then click the **Agent Assist** toggle
   to the on position.

3. In the **Knowledge \& Guidance** section, select one of the following
   options:

   - **Agent Assist Hub** . Select this option to use knowledge assist, agent
     coaching, and conversation summarization in the [**Agent Assist
     Hub**](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist-hub) panel of the agent desktop.

   - **Generative Knowledge Assist**. Select this option to use generative
     knowledge assist in the chat adapter.

4. In the **Conversation Insights** section, select the [Agent Assist
   capabilities](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#agent-assist-chat) that you want. If you select the
   **Spelling and Grammar Check** checkbox, then the following two checkboxes
   appear:

   - **Allow agents to turn on/off automatic checks**: Select this checkbox
     to let agents turn on and off spelling and grammar check in the chat
     adapter.

   - **Allow agents to select languages**: Select this checkbox to let agents
     select the language that the chat adapter uses when checking spelling
     and grammar.

5. Click **Save Agent Assist**.

### Configure Agent Assist at the queue level

To configure Agent Assist at the queue level, follow these steps:

1. In the CCAI Platform portal, click **Settings \> Queue** . If you don't
   see the **Settings** menu, click
   **Menu**.

2. Depending on the channel you want, click **Edit / View** in one of the
   following panes: **IVR (Interactive Voice Response)** , **Mobile** , or
   **Web**.

3. Click a leaf queue.

4. In the **Settings** pane, under **Agent Assist** , click **Configure** . The
   **Agent Assist Profile Configuration** pane appears.

5. In the **Platform Name** field, select a platform that you [added
   previously](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#add-an-agent-assist-platform). The **Profile Name** field
   appears.

6. In the **Profile Name** field, select a profile.

   > [!NOTE]
   > **Note:** If you intend to use the spelling and grammar Agent Assist capability, select the `spelling-and-grammar` profile.

7. Click **Save** . The **Settings** pane appears.

8. Under **Agent Assist** , click the **Enable Agent Assist** toggle to the on
   position.

   > [!NOTE]
   > **Note:** If you click the **Agent Assist** toggle to the off position, you lose your Agent Assist configuration.

### Configure Agent Assist at the team level

You can configure Agent Assist at the team level for sessions that
aren't associated with a queue. This lets you use Agent Assist with the
following session types:

- Calls to direct phone numbers

- Calls to agent extension numbers

- Outbound calls where no queue is selected

- Chats transferred directly to another agent

  > [!NOTE]
  > **Note:** When a chat is transferred, the originating agent and the receiving agent see Agent Assist as it's configured for their respective teams or queues. This also applies to transfers of direct inbound calls.

If an agent belongs to multiple teams, there's a hierarchy of priority that
determines which team's settings apply to the agent. For more information, see
[Team priority when an agent belongs to multiple
teams](https://docs.cloud.google.com/contact-center/ccai-platform/docs/add-configure-teams#team-priority-multiple-teams).

To configure Agent Assist at the team level, follow these steps:

1. In the CCAI Platform portal, click **Settings \> Users \& Teams** . If
   you don't see the **Settings** menu, click **Menu**.

2. For the team that you want to edit, click **edit icon** . The **Edit Team** pane
   appears.

3. Go to the **Agent Assist** section, and then click **arrow-down-icon** to expand the
   section.

4. Click **Configure** . The **Agent Assist Profile Configuration** pane
   appears.

5. In the **Platform Name** field, select a platform that you [added
   previously](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#add-an-agent-assist-platform). The **Profile Name** field
   appears.

6. In the **Profile Name** field, select a profile.

   > [!NOTE]
   > **Note:** If you intend to use the spelling and grammar Agent Assist capability, select the `spelling-and-grammar` profile.

7. Click **Save**.

8. Click the **Enable Agent Assist** toggle to the on position.

   > [!NOTE]
   > **Note:** If you click the **Agent Assist** toggle to the off position, you lose your Agent Assist configuration.

## Agent Assist for calls

The following call capabilities are available with Agent Assist. To
enable these capabilities, select them when you [turn on and configure
Agent Assist for calls](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#aa-turn-on-calls).

- **Knowledge assist** . Provides suggestions for knowledge articles to human
  agents during a call. These suggestions are based on the dialog between the
  agent and the end-user. An agent can examine the suggestions and decide
  which to share with the end-user. You must [create a knowledge
  base](https://docs.cloud.google.com/agent-assist/docs/knowledge-base) to use knowledge assist. For quota requirements, see
  [Generative knowledge assist](https://docs.cloud.google.com/agent-assist/docs/quotas#generative_knowledge_assist).

- **Generative knowledge assist** . Provides suggestions for generated
  knowledge articles to human agents during a call. These suggestions are
  based on the dialog between the agent and the end-user. For more
  information, see [generative knowledge
  assist](https://docs.cloud.google.com/agent-assist/docs/generative-knowledge-assist). For quota
  requirements, see [Generative knowledge
  assist](https://docs.cloud.google.com/agent-assist/docs/quotas#generative_knowledge_assist).

- **Agent coaching** . This capability is available only in the
  [Agent Assist hub](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist-hub) panel in the agent desktop.
  Agent coaching provides guidance to agents in the form of coaching cards
  that appear during a session. These cards can include guidance on what to
  say, compliance reminders, or suggestions for actions to take next.

- **Proactive generative knowledge assist** . Follows the ongoing conversation
  between an agent and end-user. It proactively provides search query
  suggestions based on the conversation context. For more information, see
  [generative knowledge
  assist](https://docs.cloud.google.com/agent-assist/docs/generative-knowledge-assist). For quota
  requirements, see [Proactive generative knowledge
  assist](https://docs.cloud.google.com/agent-assist/docs/quotas#proactive_generative_knowledge_assist).

- **Sentiment analysis** . Analyzes messages in real time from both the human
  agent and the end-user to determine emotional intent. The score is visible
  in the agent adapter. For quota requirements, see [Sentiment
  analysis](https://docs.cloud.google.com/agent-assist/docs/quotas#sentiment_analysis).

- **Real-time call transcription** . Transcribes calls in real time for agents
  to reference during the call or for analysis after the call. For quota
  requirements, see [Voice transcription](https://docs.cloud.google.com/agent-assist/docs/quotas#voice_transcription).

- **Generative AI session summarization** . Displays a generated summary in the
  agent adapter when the call enters wrap-up. If there was a single human
  agent in the session, the summary is for the entire session. If there were
  multiple human agents in the session, the session is divided into segments,
  one for each human agent that participated. In that case, each human agent
  sees a summary for the segment that they participated in. An agent can
  insert the summary, along with their own notes, during wrap-up. The agent
  can then submit the summary and notes to your CRM or external storage,
  depending on your configuration. For more information, see [Summarization
  with custom
  sections](https://docs.cloud.google.com/agent-assist/docs/summarization-with-custom-sections). For quota
  requirements, see [Summarization](https://docs.cloud.google.com/agent-assist/docs/quotas#summarization).

- **Summarization automatic evaluation** . Assesses the quality of AI generated
  summaries based on three metrics: accuracy, completeness, and adherence.
  This feature helps to evaluate the quality of summarization generators,
  which is crucial when tuning custom section definitions or upgrading
  versions that affect summarization quality. For more information, see
  [Summarization automatic
  evaluation](https://docs.cloud.google.com/agent-assist/docs/summarization-autoeval-metrics). For quota
  requirements, see [Summarization
  autoevaluation](https://docs.cloud.google.com/agent-assist/docs/quotas#summarization_autoevaluation).

### Agent experience

The following sections explain the agent experience for each
Agent Assist capability.

#### Knowledge assist

This feature follows a conversation between a live agent and an end-user
and provides the live agent with relevant document suggestions.
Agents are alerted to knowledge assist document suggestions when the
Agent Assist icon in the agent adapter has a green dot next to it.

1. Click the **Agent Assist icon** to view the suggestions in the Knowledge tab
   in the agent adapter.

2. Click the **External Link icon** next to a suggested article to share a
   document with the end-user.

#### Generative knowledge assist

> [!NOTE]
> **Note:** If a call is transferred to another agent, the knowledge articles will remain accessible to the new agent until the session ends or the transferring agent exits.

To see suggestions from generative knowledge assist, follow these steps:

1. **Start a voice call**:

   - As soon as a voice support session begins, the generative AI knowledge assist panel will become active.
2. **View knowledge suggestions**:

   - The system listens to the ongoing conversation and generates knowledge
     suggestions based on both the agent's and end-user's dialogue.

   - These suggestions appear as **Clickable tiles** in the
     Contact Center AI Platform agent voice adapter.

   - Each tile includes a **Title** and a short **Preview of the article**.
     Clicking the tile opens the full article in a new browser tab, so agents
     can view more detailed information.

3. **Searching for articles**:

   - If agents need to search for a specific topic, they can manually enter
     keywords in the **Knowledge base search** field within the same panel.

   - Matching articles will appear in a similar tile format, allowing
     agents to click through and view the content.

#### Real-Time sentiment analysis

Sentiment Analysis evaluates the conversation between a human agent and an
end-user to determine emotional intent. The analysis is generated in real-time
to display the sentiment of the present session, or as a one-time score upon
Virtual Agent escalation. Sentiment Analysis is available for both Voice and
Chat.

*For Voice*: The Sentiment feature panel displays on the Agent Adapter during a
live session.

**Sentiment Analysis breakdown**

The Real-Time Sentiment Analysis displays 3 scores: last, session, and previous
leg.

A (**--**) displays when no score is available.

|   |   |
|---|---|
| **last** | sentiment score for the last consumer response (updates in real-time) |
| **session** | current average sentiment score (updates in real-time) |
| **prev. leg** | average sentiment score of the previous segment |

There are three sentiments types (neutral, happy, and negative) in the Real-Time
Sentiment Analysis and scores displayed fall into the following ranges:

- Over 63 = Happy

- Between 38 and 63 = Neutral

- Below 38 = Negative

During the session, the Real-Time Sentiment Analysis scores are sent to the
Agent Adapter. After the session, the session's average score will be posted in
the CRM ticket.

#### Generated session summarization

If [configured](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#aa-turn-on-calls), you can add a generated summarization to
your wrap-up notes for the segment of the call that you handled.

To add a generated session summarization to your wrap-up notes, follow these
steps:

1. End a call in the call adapter. The **Wrap-up** pane appears.

2. In the **Notes** field, add your notes.

3. Click ![The Agent Assist icon.](https://docs.cloud.google.com/static/contact-center/ccai-platform/docs/images/agent-assist-icon.png) **Agent Assist**. A generated session
   summary appears.

4. Click **Insert summary** to add the summary to your notes.

5. Edit or add to the notes as needed, and then click **Submit**.

## Agent Assist for chat

The following chat capabilities are available with Agent Assist. To
enable these capabilities, select them when you [turn on and configure
Agent Assist for chat](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#aa-turn-on-chat).

- **Smart reply** . Provides chat responses to your human agents in real time
  during a conversation. For quota requirements, see [Smart
  reply](https://docs.cloud.google.com/agent-assist/docs/quotas#smart_reply).

- **Generative knowledge assist** . Provides suggestions for generated
  knowledge articles to human agents during a chat. These suggestions are
  based on the dialog between the agent and the end-user. For more
  information, see [generative knowledge
  assist](https://docs.cloud.google.com/agent-assist/docs/generative-knowledge-assist). For quota
  requirements, see [Generative knowledge
  assist](https://docs.cloud.google.com/agent-assist/docs/quotas#generative_knowledge_assist).

- **Agent coaching** . This capability is available only in the
  [Agent Assist hub](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist-hub) panel in the agent desktop.
  Agent coaching provides guidance to agents in the form of coaching cards
  that appear during a session. These cards can include guidance on what to
  say, compliance reminders, or suggestions for actions to take next.

- **Proactive generative knowledge assist** . Follows the ongoing conversation
  between an agent and end-user. It proactively provides search query
  suggestions based on the conversation context. For more information, see
  [generative knowledge
  assist](https://docs.cloud.google.com/agent-assist/docs/generative-knowledge-assist). For quota
  requirements, see [Proactive generative knowledge
  assist](https://docs.cloud.google.com/agent-assist/docs/quotas#proactive_generative_knowledge_assist).

- **Sentiment analysis** . Analyzes messages in real time from both the human
  agent and the end-user to determine emotional intent. The score is visible
  in the agent adapter. For quota requirements, see [Sentiment
  analysis](https://docs.cloud.google.com/agent-assist/docs/quotas#sentiment_analysis).

- **Generative AI session summarization** . Displays a generated summary of the
  conversation when the chat session enters wrap-up. This summary provides a
  brief overview of the chat session, including the resolution, situation, and
  action. If there are multiple segments in the session, the summary is
  available at the segment level. A segment is created each time there is a
  transfer to a human or virtual agent. The agent can insert the summary along
  with their own notes. The agent can then submit the summary and notes to
  your CRM or external storage, depending on your configuration. For quota
  requirements, see [Summarization](https://docs.cloud.google.com/agent-assist/docs/quotas#summarization).

- **Spelling and grammar correction** . Provides spelling and grammar
  suggestions for messages that agents type into the message field of the chat
  adapter. Spelling and grammar correction is available for the Mobile, Web,
  SMS, and WhatsApp channels. For quota requirements, see [Before you
  begin](https://docs.cloud.google.com/agent-assist/priv/docs/spell-grammar#before_you_begin) in the Agent Assist
  documentation.

  > [!IMPORTANT]
  > **Important:** Spelling and grammar correction is in [Preview](https://cloud.google.com/products#product-launch-stages). To enable spelling and grammar correction, contact your Google Cloud account team to request access. After you have access, the option to select **Spelling and grammar correction** appears in the **Conversational
  > Profiles** settings page. For more information, see [Create conversation
  > profile](https://docs.cloud.google.com/agent-assist/docs/conversation-profile).

### Agent experience

The following sections explain the agent experience for each
Agent Assist capability.

#### Smart Reply

Smart Reply suggests chat responses to the agent using context from the ongoing
conversation. The suggested responses are in bubbles above the text entry box.

**How it works**: Suggestions appear above the text entry field. Select the
suggestion that you want and paste it into the field and send the reply to the
end-user.

#### Knowledge Assist

This feature follows a conversation between a human agent and an end-user and
provides the human agent with relevant document suggestions.

**How it works**: The Knowledge Assist button is located in the top right hand
corner of the Agent Adapter. A pink circle indicates that articles are
available. Click the icon to show the articles. The icon expands to show a list
of articles.

Click the **Share** button next to the article to send it to the end-user.

#### Generative knowledge assist

To see suggestions from generative knowledge assist, follow these steps:

1. **Start a chat session**:

   - Once the chat session is active, Generative AI Knowledge Assist begins providing suggestions based on the conversation.
2. **View knowledge suggestions**:

   - As the chat continues, the system analyzes both end-user and agent
     messages and displays relevant article suggestions as **Clickable tiles**.

   - Each tile shows a **Title** and a **Preview snippet**. Click the tile
     to open the article in a new tab for further reading.

3. **Searching for articles**:

   - Agents can manually search for specific knowledge articles by entering
     keywords into the **Knowledge base search** field

   - Search results appear as tiles, similar to automatic suggestions, and can
     be clicked to view the article

> [!NOTE]
> **Note:** If a chat is transferred to another agent, the knowledge articles remain accessible to the new agent until the session ends or the transferring agent exits.

#### Real-Time Sentiment Analysis

Sentiment Analysis evaluates the conversation between a human agent and end-user
to determine emotional intent. The analysis is generated in real-time to display
the sentiment of the present session, or as a one-time score upon Virtual Agent
escalation. Sentiment Analysis is available for both Voice and Chat.

**Sentiment Feature Panel**

*For Chat* : The Sentiment feature panel will be displayed in an
open state **by default** for all new chats. Click the **X** or the
**Sentiment Stars Icon** to open or hide the panel.

**Sentiment Analysis breakdown**

The Real-Time Sentiment Analysis displays 3 scores: last, session, and previous
leg.

A (**--**) displays when no score is available.

| Score | Description |
|---|---|
| **last** | Sentiment score for the last consumer response. Updates in real time. |
| **session** | Current average sentiment score. Updates in real time. |
| **prev. leg** | Average sentiment score of the previous segment. |

There are three sentiments types (neutral, happy, and negative) in the Real-Time
Sentiment Analysis and scores displayed fall into the following ranges:

- 40-75 = Neutral
- Over 75 = Happy
- Below 30 = Negative

During the session, the Real-Time Sentiment Analysis scores are sent to the
Agent Adapter. After the session, the session's average score will be posted in
the CRM ticket.

#### Generated session summarization

If [configured](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#aa-turn-on-chat), you can add a generated summarization to
your [wrap-up](https://docs.cloud.google.com/contact-center/ccai-platform/docs/handle-a-chat#wrap-up) notes for the segment of the chat session that you
handled.

To add a generated segment session summarization to your wrap-up notes, follow
these steps:

1. End a chat in the chat adapter. The **Wrap-up** pane appears.

2. In the **Notes** field, add your notes.

3. Click ![The Agent Assist icon.](https://docs.cloud.google.com/static/contact-center/ccai-platform/docs/images/agent-assist-icon.png) **Agent Assist**. A generated session
   summary appears.

4. Click **Insert summary** to add the summary to your notes.

5. Edit or add to the notes as needed, and then click **Submit**.

## Interaction history

You can configure CCAI Platform to display the support interaction
history for an end-user in the agent adapter during a session. This provides
context in real time to help agents provide a better support experience and
improve handle time. Managers can also view an end-user's interaction history
while monitoring sessions in real time.

Saving session summarizations for interaction history requires integration with
a CRM or [configuring external storage](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#configure-external-storage).

### Before you begin

Before you can use interaction history, you must do the following:

1. [Set up Agent Assist](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#set-up-agent-assist).

2. Do one of the following, or both, depending on your use case:

   - Configure session summarization for calls. To do this, follow these
     steps:

     1. [Turn on and configure Agent Assist for
        calls](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#aa-turn-on-calls). In the **Agent Assist** pane, select the
        **Gen AI session Summarization** and **Call details view**
        checkboxes.

     2. Click **Save Agent Assist**.

   - Configure session summarization for chat. To do this, follow these
     steps:

     1. [Turn on and configure Agent Assist for
        chat](https://docs.cloud.google.com/contact-center/ccai-platform/docs/agent-assist#aa-turn-on-chat). In the **Agent Assist** pane, select the
        **Gen AI session Summarization** and **Chat details view**
        checkboxes.

     2. Click **Save Agent Assist**.

### Configure interaction history

To configure interaction history, do the following:

1. In the CCAI Platform portal, click **Settings \> Operation
   Management** . If you don't see the **Settings** menu, click **Menu**.

2. Go to the **Interaction History** pane.

3. Do one of the following, or both, depending on your use case:

   - For **Call** , select the **Session Summary** checkbox.

   - For **Chat** , select the **Session Summary** checkbox.

4. For **Data Retrieval**, select the period of time for which you want to
   retrieve interaction history. Retrieving interaction history doesn't delay
   the start of a call or chat session because the data is loaded into the
   agent adapter after the session connects.

5. Click **Save**.

### Configure external storage to save session summaries

If your instance is not integrated with a CRM, you need to configure external
storage to save session summaries that can appear in interaction history.

To configure external storage to save session summaries, follow the instructions
in [External storage](https://docs.cloud.google.com/contact-center/ccai-platform/docs/external-storage), while including the following steps:

1. Select the **Session Summaries** checkbox.

2. For **Session Summaries** , add a path for your session
   summaries---for example,
   `session-summaries/{simple_session_type}-{session_id}`.

### View session summaries

You can view historical and ongoing session summaries when viewing a connected
call or chat session. Each session summary includes a summary for the entire
session as well as summaries for each completed session segment.

To view session summaries, follow these steps:

1. In the CCAI Platform portal, click **Calls \> Connected** . If you
   don't see the **Calls** menu, click
   **Menu** . The **Connected Calls** pane appears.

2. In the **Actions** column, for the connected call that you want, click **More** and then **Call Details** .
   The interaction history appears in the **Call Details** dialog.

To view interaction history for a connected chat session, follow these steps:

1. In the CCAI Platform portal, click **Chat \> Connected** . If you don't
   see the **Chat** menu, click
   **Menu** . The **Connected Chats** pane appears.

2. In the **Actions** column, for the connected chat that you want, click **More** and then **Chat Details** .
   The interaction history appears in the **Chat Details** dialog.

### Agent experience

Agents can view interaction history from the agent adapter in real time.

To view interaction history from the call adapter, follow these steps:

1. Answer a call. For more information, see [Agent call
   adapter](https://docs.cloud.google.com/contact-center/ccai-platform/docs/call-adapter-calls).

2. Click **Details** . The **Call details** pane appears.

3. Click **Previous interactions** . The **Previous interactions** pane appears.
   If you have previous interactions, they appear in this pane. Otherwise,
   **No summary available** appears.

4. Click ![A clipboard icon that you click to see generated
   summaries.](https://docs.cloud.google.com/static/contact-center/ccai-platform/docs/images/clipboard-icon.png) **Generated summaries** to see generated summaries for each
   interaction.

5. Click **Forward** next to
   an interaction to see an expanded view of the generated summary.

To view interaction history from the chat adapter, follow these steps:

1. Answer a chat request. For more information, see [Handle a
   chat](https://docs.cloud.google.com/contact-center/ccai-platform/docs/handle-a-chat).

2. Click ![Details icon to open the Details pane in the agent
   adapter.](https://docs.cloud.google.com/static/contact-center/ccai-platform/docs/images/icon-person.png) **Details** . The **Details** pane appears.

3. Click **Previous interactions** . The **Previous interactions** pane appears.
   If you have previous interactions, they appear in this pane. Otherwise,
   **No summary available** appears.

4. Click ![A clipboard icon that you click to see generated
   summaries.](https://docs.cloud.google.com/static/contact-center/ccai-platform/docs/images/clipboard-icon.png) **Generated summaries** to see generated summaries for each
   interaction.

5. Click **Forward** next to
   an interaction to see an expanded view of the generated summary.