--- schema_version: "1" id: 6177f7e42f76f89eecbae69db4e59a197b4b2b9c47eca769853a1534f2b80670 title: Agentforce Considerations collection: admin version: current locale: en-us portal_url: https://docs.salesforce.com/admin/current/en-us/ai/264-0-0/copilot_considerations.md canonical_url: https://help.salesforce.com/s/articleView?id=ai.copilot_considerations.htm&release=264.0.0&type=5 source_site: help.salesforce.com content_type: documentation content_hash: 2581cc45dcf2cb108f3df899e0dff3bccee4960957dd5e58ac7d061a8ce79e34 description: Carefully review the support, limits, and considerations for AI agents. products: - Agentforce - Cross Cloud release: "264" --- # Agentforce Considerations Carefully review the support, limits, and considerations for AI agents. ### Required Editions
Available in: Lightning Experience
Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type.
![Important](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/images/icon_important.png) Important Starting June 17, 2025, Agentforce (Default) will not include new features or improvements and isn’t available in new Salesforce environments. We recommend migrating to Agentforce Employee agent for continued enhancements and support. If you plan to transition to Agentforce Employee agent or make related license changes, complete the migration of your existing Agentforce (Default) agents in advance to avoid potential disruption in agent availability. If you can't complete the migration in advance, you can create new agents after the transition, which can involve some downtime. See [Migrate from Agentforce (Default) to Agentforce Employee Agent](https://help.salesforce.com/s/articleView?id=ai.migrate_agentforce_default_to_aea.htm&type=5&language=en_US). ## Agents Support - Agentforce is included as a Covered Service in the Einstein Platform and Agentforce SOC 2 and SOC 3 reports. Agentforce is HIPAA eligible and covered under the Salesforce [Business Associate Addendum Restrictions](https://www.salesforce.com/company/legal/business-associate-addendum-restrictions/), and has also achieved ISO 27001, 27017, and 27018 certifications. - The Agentforce panel is available in Lightning Experience, the Salesforce mobile app, the Field Service mobile app, and Sales Cloud Everywhere. - The Agentforce platform supports OpenAI GPT-4o for reasoning engine calls. To use Anthropic on Amazon Bedrock as the model provider for Agentforce instead, see [Select Agentforce Model Option](https://help.salesforce.com/s/articleView?id=ai.agent_setup_select_model_provider.htm&release=264.0.0&type=5 "We recommend using the Salesforce Default model option for Agentforce, which enables Salesforce to select the best model mix for agent accuracy and performance. But you can choose an AWS-Hosted or Google Gemini model option instead."). Agent actions can make calls to other predefined LLMs. Bringing your own model isn’t supported, but custom actions that execute prompt templates can use any Salesforce-managed model. See [Large Language Model Support](https://help.salesforce.com/s/articleView?id=ai.generative_ai_large_language_model_support.htm&language=en_US). - Agentforce supports [custom and standard User Interface API-supported objects](https://developer.salesforce.com/docs/atlas.en-us.uiapi.meta/uiapi/ui_api_all_supported_objects.htm). Object support for individual standard agent actions can vary. See the reference documentation for an action for more information. - Currently, only Agentforce Service Agent can connect to enhanced Messaging channels and Bring Your Own Channel. See [Considerations for Agentforce Service Agent](https://help.salesforce.com/s/articleView?id=ai.service_agent_considerations.htm&release=264.0.0&type=5 "To use Agentforce Service Agent, consider supported functionality, usage, limitations and allowances, limits, and other issues."). - Agents have limited API support. See [Agent API Developer Guide](https://developer.salesforce.com/docs/ai/agentforce/guide/agent-api.html). - Agents aren't available for Government Cloud. - When you create an agent from a template or add a standard subagent or action to your agent, the agent metadata, subagents, and actions are copied to your agent. To protect your deployed agents and customizations, changes made to standard assets in the asset library aren't automatically applied to the agents that use them. To get changes to an agent template, create a new agent from the template and recreate any customizations. To get changes to a standard subagent or action, add the subagent or action to your agent from the asset library and recreate any customizations. ## Agent Users - Only Salesforce users with admin permissions can view or edit an agent user. - You can’t log into Salesforce with agent user credentials. - As the agent user works in Salesforce, its username can appear in the Created By, Last Modified By, or Owner fields on records or in audit fields in Salesforce. See [Configure Service Agent Access](https://help.salesforce.com/s/articleView?id=ai.agent_user.htm&release=264.0.0&type=5 "Learn how Agentforce Service agents control data access. Set up an agent user for your Agentforce Service agent and assign permissions, so your agent has everything it needs to do its job.") for more information. ## Agents Languages - Language support differs by agent type. For more details, see the [considerations for your agent type](https://help.salesforce.com/s/articleView?id=ai.agent_setup_explore_types.htm&release=264.0.0&type=5 "Learn about agent types and default templates for specific clouds and common use cases."). - Language settings apply to LLM-generated messages only. - Subagent and action instructions, including input and output instructions, are supported in English only. If you provide them in a different language, the agent's reasoning engine may not perform as expected. - Some action inputs are available in English only. - System messages, such as the agent's welcome message, are translated into the end user's language only when the end user's language is selected as an additional language in the agent's language settings. To test system message translation, change the End User Language preview condition in the conversation preview panel. - If the inputs or outputs of agent actions or associated prompt templates are in an unsupported language, those actions may not function properly. - Language support for toxicity differs from the supported languages for Agentforce. See [Einstein Trust Layer Region and Language Support](https://help.salesforce.com/s/articleView?id=ai.generative_ai_trust_lang_region.htm&release=264.0.0&type=5 "The Einstein Trust Layer detects and masks sensitive data such as personally identifiable information (PII) for multiple regions and languages."). - Some LLMs generate responses that are close variants but not exact matches for the requested locale. For example, if a user requests the French (Belgium) locale, which isn’t supported, some LLMs generate a response in the French (France) locale. ## Agents Limits - For best performance, we recommend assigning no more than 10 actions to a subagent, and 10 subagents to an agent. - You can have up to 100 agents and, within that 100, you can have one version of the default Agentforce agent. Einstein bots count towards the limit of agents. - If your licenses limit the number of a specific agent type that you can create and you reach that limit, the agent type is disabled in the guided setup. - Agent actions time out after 60 seconds. - Reasoning engine requests time out after 30 seconds. - Agent action outputs over 65,000 characters are truncated. ## Considerations for Agent Conversations - Agents stream LLM responses in conversations as the responses are received. Certain Einstein Trust Layer features are applied only to the final agent response. If a hallucination is detected after the response has started streaming, the response is deleted and a new response is generated. - Agents are optimized for questions or requests that are related to a specific topic, rather than open-ended questions that are open to interpretation. - Deactivating an agent interrupts any ongoing user conversations. Users aren’t notified that an agent is deactivated. If the agent has system messages, it sends the system error message as a response to any user messages. If the agent is deployed to the Agentforce panel, the panel is available until the user closes it, and it can’t be reopened until the agent is active. - In general, agents support one intent per utterance, so users can’t make requests that span multiple intents. Users can break more complex requests into individual messages. However, the Draft or Revise Email action can combine actions to address multiple user intents. - Agent conversations aren’t personalized based on past sessions. See Agents Limits. - Agents support small talk, but topics and number of turns are limited to ensure trust and prioritize enterprise use cases. Great for CRM! Awkward at parties. ## Considerations for Custom Actions - When you create a custom action, you can’t specify how the output appears in an agent conversation. The output is formatted automatically. - Custom actions can’t accept a list and object as input. A fix is on the way. - Custom actions that reference a prompt template can use any Salesforce-managed model. See [Large Language Model Support](https://help.salesforce.com/s/articleView?id=ai.generative_ai_large_language_model_support.htm&release=264.0.0&type=5 "Understand supported large language models (LLMs) from multiple providers for embedded features, such as Prompt Builder. Identify the Salesforce-managed models that are available out of the box. Learn how you can bring your own model (BYOLLM) by using AI Models (formerly Einstein Studio)."). - Custom actions that reference a custom prompt template support only these inputs and outputs: - Input: record information object type inputs (for example, the opportunity to summarize) ![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 Object input types are currently only partially supported due to inconsistent behavior. A fix is on the way. In the meantime, we recommend using a flow to wrap a prompt template and creating a custom action from the flow. This scenario requires detailed action instructions, so test and iterate on your instructions carefully. - Outputs: text type outputs (for example, a two-sentence summary of the opportunity) - Agent custom actions support only [custom and standard User Interface API-supported objects](https://developer.salesforce.com/docs/atlas.en-us.uiapi.meta/uiapi/ui_api_all_supported_objects.htm). - Custom actions that reference an Apex class or flow support only [primitive data types](https://developer.salesforce.com/docs/atlas.en-us.apexcode.meta/apexcode/langCon_apex_primitives.htm). For example, if a flow includes a picklist, currency, or collection resource, you can't use that flow as a reference action for a custom action. - Loading text for agent actions can be tested in preview conversations for active agents only. - When you remove a custom subagent or action from an agent, it's deleted and can't be restored. #### See Also - [Standard Agent Action Reference](https://help.salesforce.com/s/articleView?id=ai.copilot_actions_ref.htm&release=264.0.0&type=5 "Standard actions are included by default with your agents. Many standard agent actions are available to all users who have permission to access Agentforce. Other standard actions are built to work with specific clouds or products, so they require an additional license or permission. When you add a standard action to your agent, customize the action for your use case, including the underlying flow, prompt template, or other reference action.")