---
schema_version: "1"
id: 180e5b86b3761e6739a4163dc09d8f1115d825399cf0953eb082e236ce6e3b8c
title: Manage Conversation Recommendations in the Legacy Builder
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/ai/264-0-0/agent_manage_conversation_reco_employee_agents.md
canonical_url: https://help.salesforce.com/s/articleView?id=ai.agent_manage_conversation_reco_employee_agents.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: c866762e6e02920d8d71e13da77e97da8bdbdebe609a08d584f3bc443ef64ad7
description: "You can manage two types of recommendations for an Agentforce Employee agent: welcome recommendations and in-conversation recommendations. Welcome recommendations appear in the Agentforce panel when it opens from most supported record pages, list views, and Lightning app Home pages. In-conversation recommendations appear during an active conversation in response to user messages."
products:
  - Agentforce
  - Cross Cloud
release: "264"
---
# Manage Conversation Recommendations in the Legacy Builder

You can manage two types of recommendations for an Agentforce Employee agent: welcome recommendations and in-conversation recommendations. Welcome recommendations appear in the Agentforce panel when it opens from most supported record pages, list views, and Lightning app Home pages. In-conversation recommendations appear during an active conversation in response to user messages.

### Required Editions

![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/images/icon_note.png)

Note Welcome recommendations and conversation recommendations are controlled by separate settings. Turning off one setting doesn’t affect the other. For example, welcome recommendations can still appear if conversation recommendations are turned off, and conversation recommendations can still appear if welcome recommendations are turned off.

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small edition"><colgroup><col></colgroup><tbody><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;">Available in: Lightning Experience</td></tr><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;">Available in: <strong>Enterprise</strong>, <strong>Performance</strong>, <strong>Unlimited</strong>, and <strong>Developer</strong> Editions. <a href="https://help.salesforce.com/s/articleView?id=ai.agent_setup_explore_types.htm&amp;release=264.0.0&amp;type=5" title="Learn about agent types and default templates for specific clouds and common use cases.">Required add-on licenses vary by agent type.</a></td></tr></tbody></table>

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small permission">
        <colgroup>
          <col style="width:50%">
          <col style="width:50%">
        </colgroup>
        <thead class="slds-text-title_caps ">
          <tr class="">
            <th scope="col" class="slds-cell-wrap" style="text-align:center;vertical-align:top;" id="d77159e83">User Permissions Needed</th>
            <th scope="col" class="slds-cell-wrap" style="vertical-align:top;" id="d77159e86">&nbsp;</th>
          </tr>
        </thead>
        <tbody>
          <tr class="">
            <td data-label="User Permissions Needed" class="slds-cell-wrap" style="vertical-align:top;" headers="d77159e83 ">To build and manage Employee agents:</td>

            <td data-label="" class="slds-cell-wrap" style="vertical-align:top;" headers="d77159e86 ">
              <p>Manage AI Agents</p>
              <p dir="ltr">OR</p>
              <p style="margin-bottom:0;" dir="ltr">Customize Application</p>
            </td>

          </tr>
        </tbody>
      </table>

Before you begin, [set up Data Cloud](https://help.salesforce.com/s/articleView?id=data.c360_a_setup_provision.htm&type=5&language=en_US). Data Cloud is required for in-conversation recommendations only. Without it, in-conversation recommendations don’t appear, even when in-conversation recommendations are turned on. Welcome recommendations don’t require Data Cloud.

These steps apply to agents built in the legacy builder. To set up conversation recommendations for an agent built in Agentforce Builder, see [Customize Conversation Recommendations for Agentforce Employee Agents](https://help.salesforce.com/s/articleView?id=ai.customize_welcome_reco_for_aea.htm&type=5&language=en_US).

1. From Setup, in the Quick Find box, enter Agent, and then select **Agentforce Agents**.
2. On the Agentforce Agents Setup page, click the name of your agent to open its Details page.
3. From the Agent Details page, select the **System Messages** tab, and then turn on or off **Conversation Recommendations on the Welcome Screen**.
    
    You can use this option to control welcome recommendations that appear when the agent panel opens from supported record pages, list views, and Lightning app Home pages.
4. From the Agent Details page, select or clear **Conversation Recommendations in Agent Responses**.
    
    You can use this option to control in-conversation recommendations that appear during a conversation.
5. Save your changes.

- **[Customize Conversation Recommendations for Agentforce Employee Agents in Agentforce Builder](https://help.salesforce.com/s/articleView?id=ai.customize_welcome_reco_for_aea.htm&release=264.0.0&type=5)**  
    Customize conversation recommendations to suggest prompts your employees can use with your Agentforce Employee Agent, so they can select a prompt to start a conversation instead of typing from scratch. Conversation recommendations include welcome recommendations that appear on the welcome screen when the Agentforce panel opens, and recommendations that appear after agent responses during a conversation.
- **[Considerations for Conversation Recommendations](https://help.salesforce.com/s/articleView?id=ai.agent_conversation_reco_considerations.htm&release=264.0.0&type=5)**  
    Conversation recommendations include two types: welcome recommendations and in-conversation recommendations. Review these considerations before you set up conversation recommendations.