Agentforce (Default) Considerations

To use Agentforce (Default), consider supported functionality, usage, limits and allowances, and more.

Required Editions

Available in: Lightning Experience
Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type.
Important
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.

Language and Locale Support

Agentforce (Default) can generate responses in these languages.

Note
Note

Enhanced language support for Agentforce (Default) is a pilot or beta service that is subject to the Beta Services Terms at Agreements - Salesforce.com or a written Unified Pilot Agreement if executed by Customer, and applicable terms in the Product Terms Directory. Use of this pilot or beta service is at the Customer's sole discretion.

Note
Note

This list is for languages supported by Agentforce. For a list of languages supported by the Salesforce platform as a whole, see Supported Languages.

Language Code
English en_AU
en_GB
en_US
Afrikaans (Beta) af
Arabic (Beta) ar
Armenian (Beta) hy
Bengali (Beta) bn
Bosnian (Beta) bs
Bulgarian bg
Catalan ca
Chinese Simplified zh_CN
Chinese Traditional zh_TW
Croatian hr
Czech cs
Dutch nl-NL
nl-BE
Danish da
Estonian et
Farsi (Beta) fa
Finnish fi
French fr_CA
fr_FR
German de
Greek el
Gujarati (Beta) gu
Hebrew (Beta) he
Hindi hi
Hungarian hu
Icelandic (Beta) is
Indonesian id
Italian it
Japanese ja
Kannada (Beta) kn
Kazakh (Beta) kk
Korean ko
Latvian (Beta) lv
Lithuanian (Beta) lt
Macedonian (Beta) mk
Malay ms
Malayalam (Beta) ml
Marathi (Beta) mr
Norwegian no
Polish pl
Portuguese pt_BR
pt_PT
Punjabi (Beta) pa
Romanian ro
Russian (Beta) ru
Serbian (Beta) sr
Slovak (Beta) sk
Spanish es_ES
es_MX
Swedish sv
Tagalog tl
Tamil (Beta) ta
Te reo (Beta) mi
Telugu (Beta) te
Thai th
Turkish tr
Ukrainian (Beta) uk
Urdu (Beta) ur
Vietnamese vi

See Agentforce Considerations for additional language and locale support considerations.

Supported Large Language Model

Agentforce (Default) supports OpenAI GPT-4o for reasoning engine calls. 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.

Einstein Trust Layer Service Support

Agentforce (Default) supports these Trust Layer services.

Einstein Trust Layer service Description
Zero Data Retention Policy Einstein Trust Layer uses a zero-data retention policy, so no data is stored or used for model training by third-party LLMs. Customers’ use of other features including agents may result in data storage. For more information, contact your Salesforce account executive.
Dynamic Grounding with Secure Data Retrieval Relevant information from trusted company data, your knowledge base, or other sources you configure, is used to answer a question.
Prompt Defense (System policies and prompt injection detection) System policies help limit hallucinations and decrease the likelihood of unintended or harmful outputs by the LLM.
Toxicity Detection Potentially harmful LLM responses are detected and flagged.
Audit and Feedback Prompts, responses, and trust signals are logged and stored in Data 360, giving you visibility into the results of each user interaction. Feedback can be used for improving instructions, prompt templates, and more.

Data masking through the Einstein Trust Layer is disabled to improve the performance and accuracy of agents. See Trust and Agents.

Agentforce (Default) and Einstein Requests Usage

Einstein Requests is a usage metric for generative AI. The use of generative AI capabilities, in either a production or sandbox environment, consumes Einstein Requests and possibly Data 360 credits. To learn more, see Generative AI Billable Usage Types.

Agentforce (Default) is a consumption-based product that uses Einstein and stores and processes data using Data 360. Agentforce (Default) consumes credits used for billing based on your usage of the feature.

Other Considerations

Agentforce (Default) is supported in employee channels, including the Agentforce panel in Lightning Experience, Slack, the Salesforce mobile app, the Field Service mobile app, and Sales Cloud Everywhere.

  • Conversation history applies to the current session only. Messages from up to the most recent six turns, including agent and user messages, are used as context. To keep the context focused on CRM use cases, messages such as “hello” aren’t included.
  • Agentforce (Default) sessions are specific to a browser tab. A new session is started when a user refreshes their browser tab or opens Agentforce (Default) in another tab.
  • For any user request that returns a list, an agent shows up to 50 records when the user selects View More, even if the number of records is larger than 50. The 50 records are shown in a record page, not in the agent conversation.
  • If a supported agent action is triggered by a user’s request, Agentforce (Default) is aware of which page the user is on. Sometimes the agent maintains the previous page’s context when you update fields or switch between records in a conversation.
  • Agentforce (Default) can’t make proactive suggestions. Users must enter a request or ask a question to start a conversation with the agent.