#Agentforce328 人がディスカッション中

Hi everyone,

I’d like to understand whether Zoom Phone, RingCentral, and Agentforce (including Prompt Builder) can be integrated with or used within Salesforce Experience Cloud.

Specifically, I’m looking for information on the following:

1. Zoom Phone: Can Zoom Phone be integrated with Experience Cloud for making and receiving calls? Are features such as click-to-call, call logging, and CTI supported for community users?
2. RingCentral: Does RingCentral support integration with Experience Cloud? If so, what calling and telephony features are available to external or community users?
3. Agentforce and Prompt Builder: Can Agentforce agents be deployed within an Experience Cloud site? Can prompts created using Prompt Builder be used by community users, and what are the available options and limitations?
4. Licensing requirements: What Salesforce licenses, Experience Cloud licenses, Agentforce licenses, or third-party subscriptions are required to enable these features?
5. Configuration and limitations: Are there any additional setup requirements, supported integration approaches, permissions, or known limitations to consider?

If anyone has implemented these solutions, I’d appreciate details about the recommended approach, licensing costs or requirements, and any practical experience or documentation you can share.

Thanks in advance! 

I deployed an Agent Network 2.0 project (one AgentScript broker, OpenAI LLM, MCP tools) to a managed Omni Gateway in the CloudHub 2.0 shared space. I’m on a free trial org and used agent-network project deploy -g <gateway>.

The deploy succeeds. The app shows APPLIED, RUNNING, 1/1, and the broker compiles and mounts at /restaurant_broker. The pod logs this warning at startup:

LLM provider 'rm_openai_llm' at 'http://testgateway:8082/…/rmOpenaiConnection': LLM provider responded with HTTP 400 on /responses. Server is reachable but the request was rejected -- skipping strict validation.

Every request to the broker URL (agent card, root, A2A SendMessage) returns an empty HTTP 503 from “Anypoint Flex Gateway”. The pod logs show no incoming requests.

Still 503 after:

• a clean redeploy
• a fresh MCP server
• --disable-tracing
• removing the Tracing policy
• logging.level ERROR

The same project works locally in Docker. The agent card returns 200 there.

Has anyone run a broker on a free trial? Is there a shared-space limit, or a way to see why the gateway returns 503? 

Instead of shared space, I tried creating a private space. But I could not create a network in a private space in the trial account.  

We have a community demo coming up soon and we need to make it working soon.  

Any suggestion / help is appreciated.  

Org ID: 00Dbg000007XVPB (sandbox devAnis, refreshed from production 00D20000000CjigEAC).  

Data Cloud was provisioned in this org on 2026-10-20. Data Cloud Setup Home shows "Your Data Cloud instance is live and connected to your home org" (1 data space, 7 connections).

Creating an Agentforce Data Library with Knowledge articles as its source (Article__kav, content field Contenu__c, data category filter) always fails at the first step, "Ingesting data into Data Cloud", with the message "Data Cloud asset provisioning failed. Please retry". We tried Retry and recreating the library: the error is the same. 

The org contains Knowledge data streams copied from production during the sandbox refresh: Article_kav_Home, Article_DataCategorySelection_Home, DataCategory_Home and DataCategoryGroup_Home (created 2025-04-25). They are all in "Needs Activation" status and have never run. Their data lake objects already exist (for example Article_DataCategorySelection_Home__dll is ACTIVE), and Article_kav_Home is mapped in the default data space. The stream page offers no activation action, and clicking the refresh icon does not change the status. All 54 data streams in this org are in "Needs Activation". 

We also tried to delete Article_kav_Home from the Data Streams list view ("Delete Data Stream"). The UI showed "Data Stream submitted for deletion", but 30 minutes later the stream (Id 1dsSZ0000000CkLYAU) and its data lake object Article_kav_Home__dll still exist, unchanged, and no error notification was received.

The user creating the library has the System Administrator profile and the Data Cloud Architect permission set. The Data Cloud Salesforce Connector permission set (sfdc_a360_sfcrm_data_extract) has read access to Article__kav and its fields. 

Questions:

1. How can we activate or remove these pre-existing Knowledge data streams, so that the Data Library can provision its own assets?
2. Production also has Knowledge data streams. What procedure should we repeat in every sandbox refreshed from production?

#Data Cloud  #Agentforce

Hello Trailblazer Community! 👋

I have 10+ years of experience in Software QA, ETL Testing, Data Quality, SQL, Test Automation, Functional Testing, and UAT.

I am transitioning into the Salesforce ecosystem with the goal of becoming a Salesforce Functional Consultant, focusing on Sales Cloud, Salesforce CPQ, Revenue Cloud, and Agentforce.

I am currently building hands-on Salesforce portfolio projects to strengthen my understanding of business requirements analysis, business process mapping, user stories and acceptance criteria, product configuration and pricing, Quote-to-Cash processes, functional testing, and UAT.

I am particularly interested in understanding how Salesforce solutions are designed and implemented to solve real-world business problems.

I would love to connect with Salesforce Functional Consultants, Business Analysts, CPQ and Revenue Cloud professionals, Agentforce specialists, and Salesforce implementation partners.

I welcome opportunities to learn from experienced professionals, exchange knowledge, build meaningful connections, and explore relevant career opportunities in India.

If you have any advice for someone transitioning into Salesforce Functional Consulting, I would be grateful to hear your suggestions.

Looking forward to connecting with fellow Trailblazers!

Thank you!

#Sales Cloud  #Salesforce Revenue Cloud  #Salesforce CPQ & Billing  #Agentforce  #Salesforce Admin

Hi everyone,

I'm planning to run a production pilot of Agentforce Coworker

with a small group of users. Before we start, I need a way to monitor adoption, usage, logs, and key metrics to better understand how users are interacting with the solution. 

I'm looking for answers to questions such as: 

• How can I track who is using Coworker and how often?
• Is there a way to capture user prompts, responses, and interactions?
• What logs are available for troubleshooting and auditing?
• Are there any built-in dashboards, analytics, or monitoring tools for Agentforce/Coworker?
• What metrics do you recommend collecting during a pilot (adoption, success rate, user satisfaction, etc.)?

My goal is to have enough observability to evaluate the pilot's success and identify opportunities for improvement before a broader rollout. 

Any guidance, best practices, or real-world examples would be greatly appreciated. 

Thank you!