Considerations for Agentforce Employee Agent
Before setting up an Agentforce Employee agent, keep these considerations in mind.
Required Editions
| Available in: Lightning Experience |
| Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type. |
Employee Agent Language and Locale Support
Agentforce Employee agent supports these languages and locales.
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_UK
|
|
en_US
|
|
| Arabic (Beta) | ar |
| Bulgarian | bg |
| Catalan | ca |
| Chinese Simplified | zh_CN |
| Chinese Traditional | zh_TW |
| Croatian | hr |
| Czech | cs |
| Dutch | nl-NL |
| Danish | da |
| Estonian | et |
| Finnish | fi |
| French |
fr_CA
|
fr_FR
|
|
| German |
de
|
| Greek | el |
| Hebrew (Beta) | he |
| Hindi | hi |
| Hungarian | hu |
| Indonesian | id |
| Italian |
it
|
| Japanese |
ja
|
| Korean | ko |
| Malay | ms |
| Norwegian | no |
| Polish | pl |
| Portuguese |
pt_BR
|
pt_PT
|
|
| Romanian | ro |
| Spanish |
es_ES
|
es_MX
|
|
| Swedish | sv |
| Tagalog | tl |
| Thai | th |
| Turkish | tr |
| Vietnamese | vi |
See Agentforce Considerations for additional language and locale support considerations.
Employee Agent Large Language Model Support
The Agentforce platform 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.
| Model |
|---|
| OpenAI GPT-4o |
Einstein Trust Layer Service Support
Agentforce Employee agent 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 to improve instructions, prompt templates, and more. |
Data masking through the Einstein Trust Layer is disabled to improve the performance and accuracy of agents. Ask your system administrator about which Einstein Trust Layer services are enabled in your org and available for employee agents.
Usage Types Billed by Agentforce Employee Agent
Agentforce Employee agents use generative AI in prompt executions and use Data 360 to ingest, store, and process data. Use of Agentforce Employee agents impacts the consumption of billing credits in these usage types. Before deployment, work with your Salesforce account team to confirm license availability and plan credit usage.
Metered and Unmetered Consumption
Agentforce Employee agent usage is either metered or unmetered, depending on the permissions assigned to the interacting user. Unmetered usage applies if a user has the Unmetered User-Based AI permission. For more information, see Considerations for Unmetered Agentforce Usage.
Usage Types for Metered Usage
| Digital Wallet Card | Usage Type | Description | Notes |
|---|---|---|---|
| Flex Credits | Standard Action | Usage is determined by the number of standard actions called by the agent in a text conversation. Currently, every standard action called by the agent is metered as one standard action, irrespective of the number of tokens processed. Standard agent actions are actions that are available out-of-the-box. To check the list of Standard actions, see Standard Action Reference. Note Use of some standard agent actions require that a subscription has been purchased for
each user that accesses these actions, such as a subscription to Agentforce for Sales
Add-on or Agentforce for Service Add-on. To determine which subscription is required for
such standard actions, see Standard Action Reference at Standard Action Reference. While this
requirement is not technically enforced yet, users who don’t have the required add-on
license will lose access to such actions for which they don’t have a license when the
requirement is enforced. |
This usage type isn’t billed when it's associated with a generative AI action that qualifies as unmetered human context usage. For more information, see Generative AI Usage and Billing. |
| Flex Credits | Custom Action | Usage is determined by the number of custom actions called by the agent in a text conversation. Currently, every custom action called by the agent is metered as one custom action, irrespective of the number of tokens processed. |
This usage type isn’t billed when it's associated with a generative AI action that qualifies as unmetered human context usage. For more information, see Generative AI Usage and Billing. |
When you use Agentforce Employee agents, credits can be consumed in usage types on other consumption cards by related features such as Agentforce Data Library or Audit and Feedback.
Other Considerations
Agentforce Employee agents are supported in employee channels, including the Agentforce panel in Lightning Experience, Slack, and the Salesforce mobile app.
- If you plan to deploy multiple employee agents, describe each agent’s purpose, such as departmental scope or business function, to prevent overlapping subagents.
- Grant access to specific Employee agents using permission sets or profiles based on employee roles or groups.
- Connecting Employee agents to Slack or mobile apps involves additional authentication or licensing steps.
- Maintain a clear and organized conversation design and subagent structure to drive consistent performance and usability as you scale your deployment.
