Skip to main content

#Agentforce357 personnes en discutent

Agentforce is an umbrella term of the set of tools to create and customize agents as well as the collection of agents Salesforce provides across the Customer 360. Agents can either be autonomous or assistive.

Hi Salesforce Community,

I'm currently exploring Salesforce Agentforce licensing and am trying to better understand the difference between Metered and Unmetered licenses.

From the documentation and various discussions, I understand that both licensing models support Agentforce capabilities, but I'm looking for more practical guidance on when each model should be used.

Specifically, I'd appreciate clarification on the following:

  1. What exactly is considered a "metered" interaction or consumption in Agentforce?
  2. How does Salesforce measure usage under a Metered License (conversations, actions, tokens, requests, etc.)?
  3. What are the limits and cost implications of Metered Licensing?
  4. How does an Unmetered License work in comparison?
  5. Are all Agentforce features available under both licensing models?
  6. What are the recommended use cases for choosing Metered vs. Unmetered licensing?
  7. For a scenario with:
    • Internal Employee Agents
    • Customer-facing Service Agents
    • High-volume automated interactions
  8. Which licensing model would be more cost-effective?
  9. Is there any way to monitor or forecast Agentforce consumption before deciding on a licensing strategy?

If anyone has real-world implementation experience, licensing guidance from Salesforce, or lessons learned from customer deployments, I would greatly appreciate your insights.

Thanks in advance! 

 

#Agentforce #SalesforceAI #SalesforceArchitect #Salesforce Developer #Salesforce Admin

2 réponses
  1. Aujourd’hui, à 07:53
    •  Metered: Agentforce usage is charged based on consumption; for agentic usage, the main unit is generally actions, not simply tokens or conversations.  
    • Flex Credits: A standard Agentforce action currently consumes 20 Flex Credits, while custom actions are also measured by the number of actions called. 
    • Unmetered: Certain licensed users/features can use qualifying Agentforce capabilities without consuming Flex Credits, when the required licensing, permissions, and execution conditions are satisfied. 
    • Important: “Unmetered” does not mean everything in the agent is free; underlying services such as Data 360 can still consume credits. 
    • Employee Agents: Agentforce add-ons provide unmetered Agentforce usage for employees; the Agentforce User License, by contrast, provides metered employee usage and requires Flex Credits. 
    • Customer-facing Agents: Salesforce currently offers both Flex Credits (pay per action) and Conversations (pay per conversation) for customer-facing agents. 
    • High-volume usage: Consumption-based pricing makes the cost depend on actual usage, so action/conversation volume and the specific features used need to be estimated rather than assuming one fixed cost. 
    • Monitoring: Use Digital Wallet to monitor Agentforce consumption and usage in the org. 
    • Forecasting: Salesforce recommends reviewing actual Digital Wallet consumption and working with your Salesforce Account Executive for contract-specific pricing and usage estimates. 
    • Bottom line: Metered = pay according to usage; Unmetered = qualifying usage included through specific licenses/permissions. Which is more cost-effective depends on your users, volume, features, and contract—not simply whether the agent is internal or external. 

    Also, go through the doc it helps you--->

     Agentforce and Generative AI Usage and Billing | Salesforce Help

      

    Considerations for Agentforce Employee Agent | Salesforce Help

      

    Metering for Agentforce and Generative AI Usage | Salesforce Help

      

    Salesforce Agentforce Pricing | Salesforce 

0/9000

I have been doing much research to find a video that might explain from a teaching perspective the what’s, how’s and why’s behind beginning a career in Marketing through Salesforce, and have struggled to find a current (or recently released at minimum) creator that might have such content.

If anyone has any leads or recommendations I would love to check them out! Much please and thank you in advance!

#Trailhead #Marketing Cloud #Agentforce #Beginner Level #Beginner #Beginner's Guide #Total Beginner #Beginner Project #BeginnerTrack
4 réponses
0/9000

I'm working on the Agentforce Testing Center trail called Set Up Testing Criteria (https://trailhead.salesforce.com/trailblazer-community/topics/trailheadchallenges?sort=LAST_MODIFIED_DATE_DESC&search=Set+Up+Testing+Criteria&ref=unit

) 

In step 7 of the Create Test Cases section, the link for Template is not enabled.   

 

#Trailhead Challenges  #Agentforce

6 commentaires
  1. Hier, à 08:06

    Hello Link for 'Template' is given in the new Test Suit Upload Test Cases  you can  give any temporary name like 'test agent' to the new test suit agent then select einstein copilot go next next till data and then go Upload to test Tab given in screenshot where Template link is provided  

    Hello Link for 'Template' is given in the new Test Suit Upload Test Cases you can give any temporary name like 'test agent' to the new test suit agent then select einstein copilot go next next till da

     

     

     

    {913A47AC-4C1D-4F20-A2D2-84FBD9AFF01D}.png

     

     

     

0/9000
Bodala Pallavi a posé une question dans #AgentforceTesting

I’m using Conversation-Level Testing in the new Agentforce Studio Testing Center (Beta) on Summer ’26. 

I downloaded the CSV template directly from Upload Test Cases → Template, which contains: 

Conversation, Expected Actions, Expected Subagents 

However, after uploading the populated template and running the test, I receive: 

 

Turn-Level Testing works correctly with its corresponding CSV template. 

  

Is there a different column name or CSV format required for Conversation-Level Testing, or is this a known issue with the current Beta Testing Center? 

  

 

#AgentforceTesting  #Agentforce

1 réponse
  1. Hier, à 23:03

    @Bodala Pallavi

     

    What I'd try, quickly - 

    1. Populate the template without opening it in Excel if you can, or re-save explicitly as CSV UTF-8, to eliminate the encoding angle. 

    2. Check the exact header spelling and order against any current Salesforce Help doc for Conversation-Level Testing, in case the tool expects a slightly different header (for example a "Conversation" vs "Conversation Transcript" naming drift between template versions). 

    --> If both check out, treat it as a known Beta issue. Conversation-Level Testing is new in Summer '26 and this is exactly the kind of template-versus-parser mismatch that shows up in Beta.  

     

    Since the template came straight from the tool and Turn-Level works with its template, this points to a Beta bug rather than user error. I'd log it with Salesforce Support, referencing Testing Center Beta, and note that the tool-provided Conversation-Level template is rejected on upload.

0/9000

I have this agent built using agentscript and it is working just fine but my client would like to make it available on our communities as well, to allow users to access it without the need for the Salesforce app. Is there a way to deploy an employee agent? I know that Service ones are possible but I dont know if i would be able to do all the things the employee one is doing  

 

#Agentforce  #Salesforce Developer

2 réponses
  1. Hier, à 16:07

    Hi Guilherme, 

     

    Salesforce's Agentforce Deployment documentation lists the supported channels this way: Employee Agents are supported on Salesforce Lightning Experience, Salesforce Mobile, Slack, and Enhanced Web Chat — internal-only surfaces. Experience Cloud sites aren't a supported channel for Employee Agents. Service Agents are what support deployment to Experience Cloud, via Enhanced Chat/messaging channels. 

     

    So Ajaypreet's answer is on the right track: there's no supported way to deploy an Employee agent directly to a community/Experience Cloud site. Your practical path is: 

     

    1. Create a new Service Agent for the external-facing use case 

    2. Rebuild the topics/instructions/actions using AgentScript — you can largely copy over your existing AgentScript code for instructions and action logic, since the underlying script structure is similar 

    3. Deploy that Service Agent to your Experience Cloud site via Enhanced Chat / messaging channel (Omni-Channel routing) 

     

    One thing to check while migrating: Employee Agents run with the logged-in employee's own permissions/context, while a Service Agent on a community typically runs under a dedicated integration/agent user or the guest/community user's context. Review sharing rules and object/field access for whatever user the Service Agent will run as — that access model differs from what your Employee Agent currently relies on, and it's usually the part that needs the most rework, not just copying the actions over. 

     

    Reference:

    https://trailhead.salesforce.com/content/learn/modules/agentforce-deployment-quick-look/deploy-an-ai-agent-with-agentforce

0/9000

Hi everyone,

I'm currently preparing for the Salesforce Certified Platform Administrator exam and am looking for any available discount codes or free certification vouchers.

If anyone has an unused voucher or knows of any ongoing Trailhead Quests or community events offering discounts, please let me know.

Thanks in advance for your help! 

 

Email Id:  

sarvani.jonnalagadda.07@gmail.com

 

#Free Vouchers  #Agentforce  #Certification

 

 

#Discount Voucher

0/9000

Hi everyone,

Our Opportunity sharing is Public Read/Write. Reps need to use Agentforce Coworker for e.g. their own deals, but they must not be able to query KPI/performance data about their colleagues (e.g., "How many deals did XY close in month XY?").

How can we block peer performance calculations without changing CRM sharing to Private?

Thanks! 

 

#Agentforce

2 réponses
  1. 16 sept., 05:02

    Hi @Anne Gleißner Agentforce coworker uses the same permission as users. If normal users have access to opportunities of collegues then so have the coworker. In my opinion there are no as such exceptions that could be added for the coworker.

0/9000

 Hello Trailblazers, I am facing an issue with Prompt Builder in a newly created Agentforce Developer Edition (Summer '26). I created two separate Agentforce Developer Edition orgs using the official Salesforce signup page, but I am experiencing the same issue in both orgs. Einstein, Prompt Builder, and Agentforce are enabled, and I have assigned all the required permission sets, including Agentforce Default Admin, Prompt Template User, Prompt Template Manager, Agentforce Service Agent Configuration, and Data Cloud Architect. However, whenever I click Preview in Prompt Builder, I receive the error "An error occurred during generation. Prompt Engine API failed - Status: 404". When I save the prompt template, I also receive the warning "Validation service is temporarily unavailable. Template will be saved without validation." I also created a Screen Flow and used the Generate Prompt Response action, but during Flow Debug I receive the same Prompt Engine API failed - Status: 404 error. I have tried creating a very simple prompt template, tested in multiple browsers, reassigned permissions, and even created a second fresh Agentforce Developer Edition org, but the issue persists. I also noticed that Model Builder is not available in Setup, and the GenAiPromptTemplate object is not available in my org, although other GenAI objects such as GenAiPluginDefinition, GenAiPlannerDefinition, and GenAiFunctionDefinition are present. My org instance is IND168

. Has anyone experienced this issue with newly created Agentforce Developer Edition orgs? Is there an additional setup or provisioning step required for Prompt Builder, or is this a known Salesforce platform issue? Any guidance would be greatly appreciated. Thank you.  

 

#Trailhead Challenges  #Agentforce

1 réponse
  1. 15 sept., 16:13

    Hi Suresh, 

    Since you’re seeing the same 404 from the Prompt Engine API in two fresh Agentforce Developer Edition orgs, and you’ve already verified the permissions and enabled features, this doesn’t look like a permissions issue. 

    The missing GenAiPromptTemplate object and Model Builder are also good indicators that the required GenAI/Prompt Builder services may not have been fully provisioned in those orgs. 

    I’d recommend creating a Salesforce Support case and include the IND168 instance, the Prompt Engine API failed - Status: 404 error, and the fact that it reproduces in two newly created Agentforce DE orgs. Salesforce can confirm whether there’s a provisioning issue or whether an additional enablement step is required. 

0/9000

Hello Guys, 

 

I am using accApi and trying to open an agent from LWC but facing issue as the agent is not opening only the agentforce window is opening - after that as i select the agent -conversation starts. 

 

So basically in the lwc  : 

1. i am calling   --  import { open, execute, close } from 'lightning/accApi';  

2. and after getting the agent id from my apex class i doing below :  

 

           

await open(this.resolvedBotId); // i am getting the id from apex.

            console.log('Agent panel opened successfully.');

            const utterance = "Start";

            await execute(utterance, this.resolvedBotId);

            console.log('Agent successfully invoked with utterance:', utterance);

 

But i can open the agent window but proper agent is not selecting. 

 

#Agentforce  #LWC  #AgenticAI

7 réponses
  1. 15 sept., 14:44

    I feel this Implementation is still not perfect as it lands on Default agentforce agent 

0/9000

I have a Prompt Template that is invoked from a Record-Triggered Flow.

The user who triggers the record-triggered Flow does not have:

  • Prompt Template User permission 

I would like to understand the expected Salesforce behavior:

  1. Is the Prompt Template User permission required when a Prompt Template is invoked through a Record-Triggered Flow?
  2. If the triggering user does not have this permission, will the Prompt Template still execute?
  3. If the Prompt Template executes successfully, will it consume Flex Credits?
  4. Which user's permissions are evaluated when the Flow invokes the Prompt Template—the Flow-running user or the automation/system context?
  5. What is the purpose of the Prompt Template User permission if Prompt Templates can be invoked through Flow?

 

Looking for clarification based on the current Salesforce behavior/documentation for Record-Triggered Flow → Prompt Template

. 

 

#Agentforce  #Prompt Builder  #Mvp-agentforce-prompt-builder-team  #AgentforceTesting

8 réponses
0/9000