--- schema_version: "1" id: 8df82cc386156374c84432eb710257aa8aa600fde09c76a9fcc76fa69851e324 title: Agentforce and Generative AI Release Notes collection: admin version: current locale: en-us portal_url: https://docs.salesforce.com/admin/current/en-us/release-notes/264-0-0/rn_einstein_copilot.md canonical_url: https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_copilot.htm&release=264.0.0&type=5 source_site: help.salesforce.com content_type: documentation content_hash: 32a588fdd8fbf761f85fdf9ea6292803ebed3d95448f424c8d932d9ef28667a1 description: Bring the power of assistive and autonomous AI to your business with Agentforce. products: - Cross Cloud release: "264" --- # Agentforce and Generative AI Release Notes Bring the power of assistive and autonomous AI to your business with Agentforce. - **[The Agentforce Assistant Is Now Agent Optimizer (Beta)](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_dev_agent_optimizer.htm&release=264.0.0&type=5)** The integrated AI assistant in Agentforce Builder is now called Agent Optimizer, which better reflects how it helps you build, troubleshoot, and improve your agent. Previously, the assistant was called the Agentforce assistant, and the current beta experience was called the Agentforce Development Agent. The chat window heading is now Agent Optimizer, the Ask Agentforce button is now Ask Optimizer, and the setting that controls beta access is now Disable Agentforce Optimizer (Beta) in Agentforce Builder. These updates apply only to Agent Optimizer in Agentforce Builder. - **[Control Conversational Memory for AI Agents Across Your Org](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_agent_memory_toggle_conversation_memory.htm&release=264.0.0&type=5)** You can now control conversational memory for all AI agents and users across your org with a single setting. When you turn off conversational memory, agents stop creating memories and using existing ones, even if individual agents have memory enabled. Existing memories are preserved but aren't used while the setting is off. The Memory & Preferences icon also disappears from the Agentforce panel. Previously, you turned conversational memory on or off only for individual agents in Agent Script. - **[Build Reusable Skills for Agentforce Coworker](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_skills.htm&release=264.0.0&type=5)** A skill packages instructions, context, and tools into a reusable workflow for an AI agent. A prompt template returns one generated response. A skill runs a repeatable, multi-step task and can run tools, such as querying records or sending email. Create and publish the skill in Skill Builder, and then run it from Skills in Agentforce Coworker. - **[OpenAI GPT-4o and GPT-4.1 Family Reroute Date Approaching](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_openai_4o_41_family_reroute.htm&release=264.0.0&type=5)** OpenAI GPT-4o and GPT-4.1 family model requests will be rerouted January 14, 2027. - **[Claude Haiku 5.5 Is Generally Available](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_claude_haiku_5_5.htm&release=264.0.0&type=5)** The Claude Haiku 5.5 model is ready for use in production with a rate limit of 1,000 requests per minute. You can use this model in any supported feature, such as in a prompt template. - **[Claude Sonnet 5.5 Is Generally Available](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_claude_sonnet_5_5.htm&release=264.0.0&type=5)** The Claude Sonnet 5.5 model is ready for use in production with a rate limit of 1,000 requests per minute. You can use this model in any supported feature, such as in a prompt template. - **[GPT-6.1 Sol Is Generally Available](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_gpt_sol_6_1.htm&release=264.0.0&type=5)** The GPT-6.1 Sol model is ready for use in production with a rate limit of 1,000 requests per minute. You can use this model in any supported feature, such as in a prompt template. - **[Use the New Sessions and Intents View](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_observability_session_controls.htm&release=264.0.0&type=5)** Review processed and unprocessed sessions together, save the views you use most, and evaluate or export sessions from one workspace. - **[Transfer Calls to Agentforce Voice Using Real-Time Streaming](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_voice_realtime_streaming.htm&release=264.0.0&type=5)** You no longer need a dedicated static phone number or a SIP trunk configuration to route calls to your voice-enabled agent. With Real-Time Streaming, Amazon Connect can stream call audio directly to Agentforce over a WebSocket connection. - **[Automatically End Agentforce Voice Calls and Route by Disconnect Reason](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_voice_auto_hangup.htm&release=264.0.0&type=5)** Give your voice-enabled agent a clean way to end calls, and share the reason each call ended with your telephony vendor. Agentforce Voice agents end their side of a call when a caller stops responding or the call reaches its maximum duration. Enable Auto-Hangup per agent at the connection level so that the agent also ends the call when it determines that it has fully addressed the caller's request. For partner telephony, turn on Auto Disconnect in Agentforce Voice Setup so that control returns to your vendor, which can use the disconnect reason, such as Customer Intent Fulfilled, to decide how to handle each call. - **[Build and Analyze Agentforce Grid Worksheets in Plain Language with Grid Agent](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_grid_agent.htm&release=264.0.0&type=5)** Describe what you want to build or analyze in the Grid Agent sidebar, and Grid Agent configures columns or answers questions about your data. For example, ask Grid Agent to "Create a column that summarizes each case description." After you review and approve the proposed action, Grid Agent creates and configures the column. To analyze your data, ask a question such as "What patterns do you see in the Sales Stage column?" The sidebar is open by default. - **[Agents Now Default to Error Mode for File Uploads](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_file_upload_default.htm&release=264.0.0&type=5)** Agentforce agents that can receive file uploads from a client now default to error mode, so you have more control over agent file handling. Previously, agents that can receive files defaulted to auto mode, and your agent decided how to handle the file. In error mode, when someone uploads a file, the agent sends a customizable error message. If you want your agent to accept file uploads, you must add the file upload parameter to your agent’s script and specify a mode. If you don't want your agent to accept file uploads but you don't want it to send an error message, you can specify the disabled mode in the file upload parameter of your agent's script. You can also control which clients can accept file uploads. - **[GPT-6 Luna, Sol, and Astra Are Generally Available](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_gpt_6.htm&release=264.0.0&type=5)** The GPT-6 Luna, Sol, and Astra models are ready for use in production with a rate limit of 1,000 requests per minute. You can use these models in any supported feature, such as in a prompt template. - **[Claude Opus 5.5 Is Generally Available](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_claude_opus_5_5.htm&release=264.0.0&type=5)** The Claude Opus 5.5 model is ready for use in production with a rate limit of 1,000 requests per minute. You can use this model in any supported feature, such as in a prompt template. - **[Claude Opus 5 Is Generally Available](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_claude_opus_5.htm&release=264.0.0&type=5)** The Claude Opus 5 model is ready for use in production with a rate limit of 1,000 requests per minute. You can use this model in any supported feature, such as in a prompt template. - **[Free and Trial Orgs Have New Rate Limits and Model Access Rules](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_new_limits_free_trial.htm&release=264.0.0&type=5)** These changes may affect Developer Edition (DE) Orgs, Trailhead Playgrounds, and more. - **[Ground Prompt Templates with Microsoft Office, Text, and Email Files](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_prompt_builder_file_input.htm&release=264.0.0&type=5)** Prompt templates in Prompt Builder can ground generative AI requests with Word documents, spreadsheets, presentations, text, CSV files, and email files, in addition to PDF and image files. - **[Conditional Logic in Prompt Templates Is Generally Available](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_prompt_builder_conditional_logic.htm&release=264.0.0&type=5)** Conditional logic in generative AI prompt templates is generally available. Add `if`, `else if`, and `else` blocks so that one prompt template adapts based on grounded data. - **[Format Prompt Instructions with Text Styling in Prompt Builder](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_prompt_builder_template_block_editor.htm&release=264.0.0&type=5)** The Block Editor now supports rich text formatting in generative AI prompt templates. Headings, lists, bold, italic, underline, and dividers are preserved through save, **Preview**, and generative AI at run time. - **[See Knowledge Sources in Agentforce Session Details](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_observability_knowledge_sources.htm&release=264.0.0&type=5)** See Salesforce Knowledge articles and external sources your agent used in a session. Open a session from Sessions & Intents to review which sources were used to support the agent’s responses. - **[Track Voice Latency and Speech Metrics in Session Trace](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_observability_voice_metrics.htm&release=264.0.0&type=5)** Spot long Agentforce Voice silences and inspect speech-to-text and text-to-speech timing in Session Trace, including word-level automatic speech recognition (ASR) confidence. A clock icon flags abnormal agent silence. - **[Review Updated Agentforce Observability Metrics](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_observability_metric_updates.htm&release=264.0.0&type=5)** Several Agentforce Observability metric names and formulas changed. Compare latency and completion trends with the new labels, and review Success Rate with the updated calculation. Agent Interaction Duration is removed from dashboard templates. - **[Legacy Agent Builder Changing Reasoning Engine from GPT-4o to GPT-5.6 Luna](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_legacy_builder_model_change.htm&release=264.0.0&type=5)** The legacy Agentforce Builder is implementing an on/off switch to change the reasoning engine to GPT-5.6 Luna on October 15, 2026. - **[Dynamic Default Model Selection for New Agents](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_agents_new_defaults.htm&release=264.0.0&type=5)** Starting October 15, 2026, new agents created in Agentforce Builder default to an optimal model selected for them. - **[Authenticate to External MCP Servers with Per-User Credentials](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_mcp_per_user_auth.htm&release=264.0.0&type=5)** Allow Agentforce Employee agents (AEA) to act on behalf of individual users with user-based Model Context Protocol (MCP) servers. With per-user authentication, your users can access an external MCP server with their own credentials instead of a shared system-to-system connection. Eliminate shared service-user tokens and ensure a clear per-user audit trail. - **[Gemini 3.8 Flash Is Generally Available](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_gemini_flash_3_8.htm&release=264.0.0&type=5)** The Gemini 3.8 Flash model is ready for use in production with a rate limit of 1,000 requests per minute. You can use this model in any supported feature, such as in a prompt template. - **[Spend Less Time on Manual Testing with the Agentforce Assistant (Beta)](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_dev_preview.htm&release=264.0.0&type=5)** The Agentforce assistant no longer just suggests changes to your agent. Now it can test them for you, too. When the assistant suggests a change, it automatically runs previews in simulate mode to validate your agent’s basic functionality and its performance against variations and edge cases. Then it iterates until your agent behaves as expected, so you can accept the assistant’s changes with less manual verification. You can also prompt the assistant to test your own changes. For example, ask it to run a specific subagent through different personas and refine based on the results. - **[Azure OpenAI o3 Family and o4-mini Reroute Date Approaching](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_openai_o3_family_reroute.htm&release=264.0.0&type=5)** Azure OpenAI o3 family and o4-mini model requests will be rerouted November 11, 2026. - **[Upgrade Einstein Bots to Agentforce Service Agent (Generally Available)](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_bots_upgrade_tool.htm&release=264.0.0&type=5)** The Upgrade Agent tool, previously available in beta, is now generally available. Use the tool to convert an Einstein Bot to an Agentforce Service Agent. The tool creates the new agent separately, so your existing bot remains available while you review and configure the new agent. - **[Let Agentforce Agents Remember What Matters to Your Users (Generally Available)](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_agent_memory.htm&release=264.0.0&type=5)** With Agent Memory, your Agentforce agents recall relevant details from your users' past conversations, so your users don't have to repeat themselves. Agents also reference profile details, such as a user's name, from the first message, so responses feel personalized from the start. Previously, agents had no memory of past conversations, so your users had to restate the same details every time they started a new conversation with an agent. - **[Preview Custom Lightning Types in Agentforce Builder with Fewer Steps](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_clt_preview_local.htm&release=264.0.0&type=5)** Preview Custom Lightning types (CLTs) in Agentforce Builder for actions you create or customize directly in an agent. CLTs are used to customize the UI for agent action inputs and outputs for a more branded, interactive experience. Previously, CLTs didn't render in preview for actions created or customized in an agent in Agentforce Builder. You had to recreate the action in the asset library. You also had to commit your agent before CLTs rendered at all. Now, CLTs render for actions in preview no matter where you created or modified them, or whether your agent is in a draft or committed state. - **[Learn How to Optimize an Agent by Analyzing Production Data](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_optimize_agent_example.htm&release=264.0.0&type=5)** We added documentation that shows you how to headlessly analyze production data to identify suboptimal agent responses. Your AI assistant identifies root causes, turns them into durable test cases, and suggests fixes, which you validate against a full test suite in your testing environment, such as a sandbox, before promoting to production. - **[Learn How to Ground an Agent with an Agentforce Data Library](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_ground_agent_adl_example.htm&release=264.0.0&type=5)** We added documentation that shows you how to develop an agent, ground it with an Agentforce data library, test, and activate it. This example shows you how to complete the steps by using headless (using an AI coding assistant), or Canvas (using the Salesforce UI) paths. - **[Learn How to Build and Deploy an Enhanced Chat Agent](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_build_enhanced_chat_agent_example.htm&release=264.0.0&type=5)** We added documentation that shows you how to build a chat agent, test and activate it, and deploy it to an Enhanced Chat v2 channel. This example shows you how to complete the steps by using headless (using an AI coding assistant), Canvas (using the Salesforce UI), or Agent Script (using code) paths. - **[GPT-5 Family (GPT-5, GPT-5-Mini, GPT-5-Nano, GPT-5-Pro) and O3 / O3-Pro Reroute Date Approaching](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_gpt_5_reroute.htm&release=264.0.0&type=5)** GPT-5 Family and O3 / O3-Pro model requests will be rerouted December 11, 2026. - **[Help Customers Continue Ended Sessions in Enhanced Chat v2](https://help.salesforce.com/s/articleView?id=release-notes.rn_ecv2_continue_conversation.htm&release=264.0.0&type=5)** After a messaging session times out or ends in Enhanced Chat v2, customers can easily resume it by clicking Continue Conversation in the chat window. - **[Give Customers a Smoother Conversation Experience in Enhanced Chat v2](https://help.salesforce.com/s/articleView?id=release-notes.rn_ecv2_conversation_view_updates.htm&release=264.0.0&type=5)** Enhanced Chat v2 now delivers a smoother, easier-to-follow conversation experience. When a customer sends a message, it stays in view while the response loads instead of scrolling out of sight, so customers can read replies in context. The avatar now appears above the Send Message text field for a cleaner layout. - **[Give AI Agents More Context with File Uploads](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_file_upload.htm&release=264.0.0&type=5)** Agentforce Service and Employee agents now support file uploads in production and preview conversations, so you can help your agents resolve more inquiries. When you add file upload support to your agent, your users can share screenshots, receipts, and PDFs by attaching a file in the chat window. Your agent can interpret the image or PDF content and answer questions, and it can add the file to a Salesforce record or use the file as context. File uploads are supported for agents connected to web clients on Enhanced Chat v1, Enhanced Chat v2, and Lightning Experience. - **[Control How Agent Action Outputs Appear on a Connection](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_agentforce_render.htm&release=264.0.0&type=5)** Always format an agent action's output the same way on a specific connection with the render nested inline action. If you don't specify an adaptive response format, Agentforce decides which one to use during the conversation. You can also format an action's output as JSON so that a connection can receive the action's structured data directly. And, with show\_and\_return nested inline action, you can now tell the agent to send a response and end reasoning at the end of an action. - **[Customize Agent Behavior Across Channels with Connection Instructions](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_agentforce_connection_instructions.htm&release=264.0.0&type=5)** Guide how your agent reasons and responds on the Messaging, Service Email, or Marketing Email connection with customizable connection instructions. For example, you can tell the agent to ignore disclaimers in emails or to use a specific response format for certain messages. - **[Customize Agent Responses with Dynamic Messaging Components](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_agentforce_custom_response_format.htm&release=264.0.0&type=5)** Create custom response formats based on messaging components, including the enhanced link, question with static options, question with dynamic options, time selector, and form components. Use the output of an agent action to populate dynamic content in your custom response formats. For example, have an agent action gather the details for a return request and then populate a custom form for the customer. - **[Easily Compare and Merge Agent Versions in Agentforce Builder](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_agentforce_compare_versions.htm&release=264.0.0&type=5)** Copy improvements from one agent version to another with a few clicks. You can now compare two versions and merge changes from one into another in Canvas and Script view. - **[Keep Field Generation Responses Focused on Business Use Cases](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_prompt_builder_template_field_gen.htm&release=264.0.0&type=5)** By default, field generation follow-up refinement requests aren't validated to ensure relevance to business requests. This means users can make unrelated, non-business requests within the field generation panel. To steer users back to your specific business goals, turn on the new Validate Field Generation Refinements setting in Setup. This limits the agent's focus entirely to field generation-related activity, ensuring your Einstein credits are spent only on relevant business use cases. - **[Field Generation Refinements Now Respect Your Selected Model](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_prompt_builder_template_field_gen_model.htm&release=264.0.0&type=5)** Previously, follow-up responses from Einstein in the field generation panel used the Salesforce default LLM instead of the model assigned to your field generation prompt template. Follow-up and refinement responses are now generated from the model that you selected in the prompt template. - **[Gemini 3.7 Flash Is Generally Available](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_gemini_flash_3_7.htm&release=264.0.0&type=5)** The Gemini 3.7 Flash model is ready for use in production with a rate limit of 1,000 requests per minute. Use these models for certain functionality, such as in a prompt template. - **[Gemini 3.6 Flash Is Generally Available](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_gemini_flash_3_6.htm&release=264.0.0&type=5)** The Gemini 3.6 Flash model is ready for use in production with a rate limit of 1,000 requests per minute. Use these models for certain functionality, such as in a prompt template. - **[Gemini 2.5 Pro, Flash, and Flash-Lite Reroute Date Approaching](https://help.salesforce.com/s/articleView?id=release-notes.rn_einstein_models_gemini_2_5_reroute.htm&release=264.0.0&type=5)** Gemini 2.5 Pro, Flash, and Flash-Lite model requests will be rerouted October 20, 2026. Gemini 2.5  Pro and 2.5 Flash will be rerouted to Gemini 3.5 Flash, and Gemini 2.5 Flash-Lite will be rerouted to Gemini 3.5 Flash-Lite. We recommend that you test your prompts and applications with the new model in Prompt Builder and AI Models as soon as possible, because expected responses can change. - **[Move Agents Between Orgs More Easily with Simplified Agent Metadata Types](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_metadata.htm&release=264.0.0&type=5)** Starting in API version 68.0, we’ve streamlined Agentforce agent metadata types to make it easier to retrieve and deploy agents. Previously, moving an agent from sandbox to production required at least three metadata types. Plus, you had to manually add every Apex class, flow, and prompt template associated with an agent action, making sure to indicate the correct agent version. With the new AiAgentDefinition and AiAgentDefinitionVersion types, Salesforce CLI now retrieves the agent and all its dependencies automatically. - **[Agentforce Platform Enabled by Default](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_auto_enable.htm&release=264.0.0&type=5)** In Winter ’27, the Agentforce platform is enabled by default for all orgs with Agentforce access, as granted by SKUs, licensing, and editions. New orgs are enabled at creation, and existing orgs will be auto-enabled. The Agentforce setting will be removed from the Agentforce Agents page in Setup, so you can build, test, and deploy agents with one less step. The platform is enabled at no additional cost and there are no changes to billing. - **[Global Expansion for Agentforce Voice with Dynamic Routing](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_voice_dynamic_routing_global_expansion.htm&release=264.0.0&type=5)** To expand the reach of Dynamic Routing, we are continuously adding local phone numbers in more countries throughout this release. - **[Dynamic Routing for Agentforce Voice Is Now Available in Japan](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_voice_dynamic_routing_japan.htm&release=264.0.0&type=5)** Dynamic Routing now supports local phone numbers in Japan. To connect to the voice-enabled agent, call the reserveRoutableNumber API, and then forward the call to the local number. - **[Show Full Conversation History in Post-Call Transcripts for Agentforce Voice Calls](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_voice_post_call_transcript.htm&release=264.0.0&type=5)** The Enhance Conversation component in the Service Console now displays consistent transcripts during and after a voice call handled by a voice-enabled agent. When the agent transfers the call to a service rep, the voice call record for the rep-customer conversation (VC1) now shows both the agent-customer and rep-customer transcripts after the call, matching what was visible during the call. Previously, VC1 showed both transcripts during the call but dropped the agent-customer transcript after the call ended. - **[Agentforce Voice Now Enforces the Limit on Procured Phone Numbers](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_voice_enforce_phone_number_limit.htm&release=264.0.0&type=5)** Agentforce Voice now enforces the Salesforce Voice (Native Telephony) limit on the number of phone numbers that you can procure. In production orgs, your Agentforce Voice license determines the limit. In sandbox and trial orgs, the limit is 10 phone numbers regardless of your license. Previously, these limits weren't enforced. - **[Pass Context with Custom SIP Headers and Disconnect with REFER in Agentforce Voice](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_voice_sip_headers.htm&release=264.0.0&type=5)** Capture custom SIP X-headers from inbound calls to deliver contextual information, such as customer intent, language preference, or case history. Configure your escalation and fallback flows to return or modify headers using the SIP REFER method when disconnecting or transferring calls. - **[Extend Agentforce Solutions with Multi-Agent Orchestration (Generally Available)](https://help.salesforce.com/s/articleView?id=release-notes.rn_agentforce_multi_agent_orchestrate.htm&release=264.0.0&type=5)** Extend your agent’s capabilities with Multi-Agent Orchestration for Agentforce. Connect your Agentforce agent with other specialized Agentforce agents in your Salesforce org. Together they collaborate on complex tasks to deliver amazing outcomes for your business.