Skip to main content
グループAgentblazer Community Group
グループ

Agentblazer Community Group

Welcome, Agentblazer! Are you ready to connect with AI leaders and enthusiasts from around the world? You've come to the right place. The Agentblazer Community is the premier destination to skill up on AI, discuss best practices, gain access to Agentforce product experts, showcase your expertise, and supercharge your career.
質問する...
Joel Primack
10月16日 15:07

🚨 Action Required: Transition your legacy Agentforce Builder model

 

What’s Changing? 

OpenAI is deprecating the GPT-4o model currently powering our legacy Agentforce Builder reasoning engine.  Starting October 15, 2026, you have two options to keep your agents running smoothly: 

 

  • Option 1 (recommended): Upgrade to the new Agentforce Builder
    • Move your agent to our new builder to unlock enhanced features and long-term support. Review this Help article for instructions on how to upgrade your agent to the new Agentforce Builder.

 

  • Option 2: Change the reasoning engine model on your agent within the legacy builder 
    • Toggle your reasoning engine to the newly supported OpenAI GPT-5.6 Luna model. Review this Help article for instructions.

 

Next Steps & Testing:

Changing your reasoning engine model or migrating to the new builder can impact your agent’s responses. We strongly recommend testing your agent thoroughly and updating its configuration as needed to ensure expected behavior before switching in production. 

 

Please reference the Help articles linked above for next steps on how to change the model in the legacy builder or consider migrating the agent to the new Agentforce Builder. 

 

Explore the 🆕 Agentforce Builder with Agent Script 

Explore the Agentforce deployments that are in production today with customers using the new Agentforce Builder. 

 

Read more about the new Agentforce Builder and here’s the page for you to learn about Agent Script. 

 

🗣️ Questions specific to your Agentforce deployment

Please reach out to your Account Executive if you have additional questions or need support.

4 件のコメント
  1. Joel Primack
    10月23日 15:12

    Hi @Lim Chong Meng – So glad to hear you're able to see the articles now! 

     

    OpenAI GPT-5.6 Luna model is specifically noted above as a model available to customers who wish to remain on the legacy builder, so they can switch the model that's powering their agent in production today. 

     

    In the new builder, you'll have the option to select the model that best aligns to your use case from the set of available ones from a number of different providers.

コメントを記入...
0/9000
Beth Marshall (Salesforce の Business Development Representative)
10月7日 1:32
Could Agentforce help improve a duplicate review process, particularly for the scenarios where existing Salesforce matching logic does not identify potential duplicates? Could Agentforce flag likely duplicates for a user to review?

Could Agentforce help improve a duplicate review process, particularly for the scenarios where existing Salesforce matching logic does not identify potential duplicates? Could Agentforce flag likely duplicates for a user to review?

3 件の回答
  1. Vishal Soni (MIDCAI CONSULTING)
    10月23日 6:39

    Hi @Beth Marshall

    , 

     

    Yes, and it’s a good use case, but I wouldn’t hand the whole job to the LLM. Here is what we tried and suggest: 

    1. Narrow the candidates first. Use SOSL, a looser matching rule, or Data Cloud Identity Resolution with fuzzy match rules to pull a small set of possible matches. Don’t ask the LLM to scan the whole database.
    2. Let the LLM judge similarity. Pass the record and its candidates to a Prompt Builder template that returns a likely duplicate yes or no, a confidence score and a short reason. This catches what string matching misses: nicknames, abbreviations, “Ltd” vs “Limited”, typos, and moved addresses. It’s a semantic problem, not a string match.
    3. Keep a human in the loop. Invoke it from Flow or Apex, create a review record or task for likely matches, and let the user decide on the merge. Don’t auto-merge.

     Hope this helps.

回答を記入...
0/9000
Joel Primack
10月21日 12:48

The Agentblazer Adoption Playbook is live 🚀

 

How do you get real value from AI agents? Nine builders shared what they built, where they got stuck, and what they'd do differently. The playbook has 5 chapters and 4 take-home tools. 

 

🎯 Customer outcomes from Agentforce

  • Workday: 21% case deflection by the end of Q1, double the 10% target
  • Datasite: 82% case deflection on its Agent Script rebuild
  • MIMIT Health: 459% ROI in three months
  • Southwest Airlines: $6M projected annual savings and 7× ROI

 

📖 What's inside

1️⃣ Start with a Metric that Matters: Andrea Simon and @Rushikesh Choudhury from Workday, plus @Chris Emmett from Capgemini 

2️⃣ Ship the Smallest Winning Use Case: Sarah Morton formerly with Engine 

3️⃣ Context Beats Perfection: Dr. Romi Chopra with MIMIT Health and @Cecilia Chiderski with CLD Partners 

4️⃣ Build It Right: @Sally ElGhoul from Code with Sally and @Grant Roberson from Datasite 

5️⃣ Scale What Works: @Ishrat Bhatti from Southwest Airlines 

 

🧰 Take-home tools

  • Plan Your Use Case
  • Choose Your Pilot Path
  • Build Your Business Case
  • Set Up Your Center of Excellence

 

👉 Read the playbook

2 件のコメント
コメントを記入...
0/9000
Piers Anderson (Tiger Communications plc の Chief Information Security Officer)
10月19日 8:57
Is there a way to find out which users are spending the most flex credits on Coworker?

We have more users than agentforce seats, but enough to give some heavy users unmetered access

4 件の回答
  1. shefali tanwar (Trail Guild)
    10月19日 9:25

    The quickest path is to query the TenantEnrichedUsageEvent object via the Query Editor, or use Data Cloud to build a custom report mapping those consumption insights directly to individual user IDs. If you just need a quick look at token volume, you can also spin up a regular Salesforce report using the GenAIGatewayRequest logs grouped by user.

回答を記入...
0/9000
Andy Engin Utkan (BRDPro Consulting の Salesforce MVP | Founder of Flow Canvas and Salesforce Break) が「#Agentforce」で投稿
7月26日 3:32

New Salesforce Break content:  

This AI Coworker Saw What Humans Missed: Agentforce Coworker

(YouTube video) 

Agentforce Coworker Applied: Enterprise Intelligence at Your Fingertips

(article) 

Is Setup with Agentforce Ready for Prime Time?

(article) 

Should You Use Roll Back Records in Salesforce Screen Flows?

(article - best practice series) 

Is Hardcoding Ids a Good Idea in Salesforce Flows?

  (article - best practice series) 

Enjoy 

 

 

 

 

 

 

#Agentforce  #New Releases  #Flow  #Best Practices

7 件のコメント
コメントを記入...
0/9000
Andy Engin Utkan (BRDPro Consulting の Salesforce MVP | Founder of Flow Canvas and Salesforce Break) が「#Flow」で投稿
10月18日 3:11

What's new on Salesforce Break: 

Winter '27 Flow Tips Every Admin and Developer Needs Right Now

(YouTube) 

Collection Filter Criteria Resource in Salesforce Flow

 

Keep Business Logic Outside Your Flow

 

 

#Flow  #Flows  #New Releases  #Architects

3 件のコメント
コメントを記入...
0/9000
Siva Ramakrishna Reddy Paipati (Cognizant の Developer)
4月30日 22:29
Clickable URL showing as URL-Redacted in Employee Agent Action

I am working on an Agentforce Employee Agent and created a prompt template to summarize records and generate clickable record links. 

 

Prompt used:

  

“Use your intelligence and provide the full clickable URL to access the record in the format: lightning/r/<Object>/<Id>/view.” 

 

In the prompt preview, I can see the full link correctly, for example: 

https://<mydomain>.lightning.force.com/lightning/r/Case/500XXXXXXXXX/view

. 

 

However, when I add this prompt as an Action inside the Employee Agent, the clickable link is displayed as URL_redacted

. If I ask the agent again in a follow‑up utterance to provide the links, it then returns them correctly. 

 

Please advise if there is a solution or configuration that can prevent the link from being redacted when used within an Employee Agent Action.

13 件の回答
  1. Aayush Das (Cognizant)
    10月15日 13:23
    Add #DisableURLRedaction# under agent description in agent script
回答を記入...
0/9000
Joel Primack
10月15日 12:23

The Agentblazer Collection 🗞️

           

What is it? 

The Agentblazer Collection is a weekly post shared in the community with resources from Salesforce related to Agentforce, community-contributed resources, and other exciting items ✨   

  

Community Contributed Resources:

For a resource be considered for a future post of The Agentblazer Collection, please share content with us by using the workflow. 

 

Featured Resources this Week:

 

Hope your week is going well!

コメントを記入...
0/9000
Joel Primack
10月14日 16:12

Dreamforce 2026 is in the books, and our job-ready agents are ready to help you achieve outcomes! 🎉 

 

Dreamforce was all about taking production agents to the next level. Two reads will get you up to speed:

  • Meet the job-ready agents. Pre-built agents for specific roles, like Piper for inbound pipe gen, Paige for IT and HR service, and Marshall for the back office. Most are GA now, and Hunter (outbound sales) is pilot now with GA in November '26. Customers are already seeing results, like Asana driving 4x the conversation volume with Piper. 👉 Read the announcement
  • Catch every Dreamforce 2026 announcement. 21 launches in one place, including Agentforce Coworker, long-horizon agents, Agent Optimizer, and AI Skills. 👉 See all 21 announcements

 

Which announcement are you most excited about?

コメントを記入...
0/9000
Vaidik Savaliya (Kriit Technologies Private limited の Developer)
10月14日 5:52
I want to join slack group, so could you please add me to your community Slack group?

Hello ,

Could you please add me to your Agentblazer Community Slack group?

My email address is vaidiksavaliya2@gmail.com.

Thank you!

1 件の回答
回答を記入...
0/9000