Skip to main content
Group

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.

Hi I created a prompt to have a summary of the activities of an account 

I thought it would be easy with the instruction : Data to use :{!$RecordSnapshot:Account.Snapshot} 

(I use the Field Generation template) 

But in reality, it's not simple because I only got the future events and tasks. 

I had to build a flow to get all activities. 

Is it so, or did I miss something ?

3 answers
  1. Aug 20, 3:51 PM

    Hi Hugues - you did not miss anything, that is expected. Activities are a special case: an Account surfaces them through TWO separate related lists - Open Activities (future events + open tasks) and Activity History (completed tasks + past events). The Account RecordSnapshot gives you the open/future set, so a summary grounded only on the snapshot naturally comes back with just upcoming events and open tasks, not the completed history you actually want to summarize. 

     

    So your Flow is the right call, not a hack. For a full activity summary you feed the data in yourself: a Flow (or Apex) that queries the Tasks and Events (or ActivityHistory + OpenActivity) filtered to the Account, then pass that collection into the prompt as a resource. That is the supported pattern - template-triggered prompt flows exist exactly for grounding on data the snapshot cannot give you. 

     

    Tip: cap and sort what the Flow returns (e.g. last N activities by date) so you stay within the prompt's context limit and the model summarizes the most relevant ones. 

     

    If this helps, please mark it as the Best Answer so it helps the next person - thanks :)

0/9000

💙 Agents are making an impact at organizations!

 

Salesforce just published the second edition of the 

Agentic Enterprise Index — and the numbers tell a pretty wild story about where the Agentic Enterprise is headed. 

 

A few stats that jumped out:

  • AI Agents built on Agentforce produced 734M Agentic Work Units (AWUs) as of April 2026 — growing 15% month-over-month
  • Businesses now run 13 agents on average, and deployment time has fallen 53%
  • Agent-driven retail sales have grown 4x
  • In regulated industries, Financial Services saw a 13x AWU growth

 

The report tracks trends from February 2025 to April 2026 across real businesses actually using agents — not just talking about them. 

 

➡️ Check out the full Agentic Enterprise Index

4 comments
0/9000

🚀 5 Reasons to Move Your Agent to the New Agentforce Builder with Agent Script

  

Agent Script is here — and it's a big step up from the legacy Agentforce Builder. It combines deterministic logic with LLM reasoning (hybrid reasoning), giving you more predictable, reliable agent behavior — plus built-in observability, flexible build options (Canvas, Script, VS Code, CLI, or AI coding tools), and first access to all future Agentforce innovation like Voice and multi-agent orchestration. 

 

✨ Good news — moving is straightforward, and both the new Agentforce Builder and Agent Script are included with your existing Agentforce purchase. 

 

 👉 Read the 5 Reasons to Upgrade Your Agent to Agent Script

0/9000

Trailhead Tuesday!

 

Discover how to blend digital accessibility and agentic AI to build truly inclusive experiences for everyone. 💡 

 

From the badge, you'll learn:

  • The essential intersection of digital accessibility and artificial intelligence
  • How to address AI bias and navigate ethical challenges responsibly
  • Strategies to design, test, and advocate for accessible AI products

 

Learn about accessible AI design in the badge today.

0/9000

 

It’s alive... but is it scalable?

 

It’s alive... but is it scalable?

🧟‍♂️ 

 

Season 1 of The Franken Org Podcast: Technical Debt Autopsy is officially out in the wild!

If your org has a Slack thread from 2021 that just says "Ship it, we’ll fix it later"

(spoiler: nobody fixed it), 11 Apex triggers on a single object, and 418 unused fields... this season was recorded specifically for your therapeutic healing. 

 

🎧 Listen/Watch now on your favorite platform:

💬 We need your feedback! Drop your thoughts, favorite anti-patterns, or worst org horror stories in the comments. Your feedback is critical for us as we prep Season 2

 

@Salesforce Developer Group, Dubai, UAE @Agentblazer Community Group @* Salesforce Developers * @WFD Partner Cohort: TDX2630DaysChallenge 

0/9000

Hi there, 

 

i am looking for the insight on the following problem from people who successfully implemented and went live with the following scenario and may address the issues with verified in practice solutions.  

 

we have implemented a service agent that must be exclusively grounded in the knowledge base with multiple subagents that share only one custom prompt action (now) that triggers the retriever (custom) with a related search index (vector search, with multilingual e5 large embedding model, on knowledge article object (data cloud). the agent is a service agent built in the new builder. prompt llm model is gemini 2.5 pro. 

 

the knowledge base (standard sf knowledge solution) contains only 89 articles 9some very long, some shorter) but the information is law related and it is very complicated, it is all in English whereas the agent should support also the conversations in French, Spanish and Portuguese (as of now, we also need to roll out other languages after they stop being beta). 

 

the subagents instructions and the prompt are also in english. 

 

the problem we have (as of now there are 2 main levels):  

1. agent wise: when the question (that was previously checked in english and returned a good answer) is asked in other languages  the agent either does not understand the question at all or when it does understand it  the answer comes back but is not satisfactory.  

2. search index/retriever wise: when tested directly in the retriever we see that the scoring for the same chunks is lower significantly for other languages in comparison with the tested same question in english (open question if the scoring indeed passes together with chunks to LLM). to patch this we added keywords to knowledge articles in multiple languages, it helps but does not fix the problem. 

 

the main proposed solutions (also by salesforce): 

1. translate the knowledge base to all those languages we want the agent to speak (which still leaves open the fact that all the instructions and the prompt are in english).  

2. normalize the query (user input) by translating it first to english and then query it while sending to prompt original language, original question and the translated english question. very simplistic description, understandable there is much more to it.  

 

it feels that such behaviour must be handled totally out of the box and all proposed solutions are intuitive but feel an overkill for something that just should work. 

 

is there anything i am missing? any insight will be very much appreciated.  

 

Thank oyu 

Yuliya 

 

 

 

 

 

0/9000

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:

 

Have a great day, Agentblazers!

3 comments
  1. Aug 12, 6:19 AM

    Hi Sir, 

    I came across your post and felt an immediate connection to your mission. I have 11+ years of CRM testing and leadership experience, 

    including 2.5 years  for the

    Gavi (COVAX) Salesforce project during the pandemic.

    Recognized for my dedication and leadership (including receiving awards like the Bravo Award for project success), I specialize in Salesforce Sales Cloud, Jira, and Xray.  

    For the COVAX project, I successfully built a comprehensive regression test library completely on my own for the entire project and structured it within Jira to streamline our workflows.

    I am currently on a planned career break and would love to give back by offering my time and expertise on a pro-bono/volunteer basis to support project-centric non-profits like yours.  

    Whether you need help navigating Salesforce data flows, optimizing test processes, or refining your tracking in Testing Perspective,  

    I am ready to jump in and add immediate value.

    I would love to connect and share how my background can help support your Project. 

    Regards, 

    Srinivasa 

0/9000

Trailhead Tuesday! 

 

Modernize your contact center by evaluating Voice options and planning your transition from Open CTI. ☎️ 

 

From this badge, you'll learn:

  • The essential steps to prepare your organization for Open CTI retirement.
  • How to evaluate and choose the best Voice platform for your customer service needs.
  • Strategic planning for a seamless transition to set your team up for success with Agentforce.

 

Get ready to up-level your customer service 🚀

0/9000

RSVP : https://trailblazercommunitygroups.com/j/4jmakxrwseerp/

 

RSVP : We're building FrankenForce a (fictional, don't worry) online clothing store for Frankenstein's monsters live, from scratch, using Agentforce. Every session we stitch on a new capability.

We're building FrankenForce a (fictional, don't worry) online clothing store for Frankenstein's monsters live, from scratch, using Agentforce. Every session we stitch on a new capability. This week: we give our monster its first working agent, Igor, the Shopping Assistant. 

 

No prior Agentforce experience required. Come for the jokes, stay for the Agent Script. All code goes public on GitHub after every session build along, fork it, break it, make it yours. 

 

@Salesforce Developer Group, Dubai, UAE @Agentblazer Community Group @* Salesforce Developers * @* Salesforce Developers *

 

 

0/9000

Trailhead Tuesday! 

 

Your Trailhead experience just got more personalized 👤 

Today, Trailhead is rolling out a redesigned Today page that makes it easier to discover what to learn next and build the skills to succeed in the Agentic AI era. 

 

And soon you’ll see features like AI-generated Trailmixes that instantly create personalized learning paths to build the right skills faster. Instead of searching through hundreds of badges, you’ll be able to simply describe what you want to learn and Trailhead builds the path for you. 

 

➡️ Go to Trailhead today to check it out!

1 comment
0/9000