小组 Agentblazer | 讨论 | Salesforce Trailblazer Community

📖 New guide alert: Everything You Ever Wanted to Know About Agentforce Voice (But Were Afraid to Ask)

If you've been curious about Agentforce Voice — how it works, how it's architected, and where it's already delivering real ROI — this guide is for you.A few highlights from the guide:

Voice isn't a separate product. It's a capability that extends the agents you've already built, carrying over your existing configuration, knowledge grounding, and escalation logic.
6 surfaces to deploy on — from standalone telephony integrations (Amazon Connect, Genesys, NICE, Vonage) to Voice on Web Chat, Voice Mobile SDK, and even Voice Notes on WhatsApp.
Real customer results: Florida Prepaid handles 75% of business-hours calls and 100% of after-hours cases with AI. Canada Goose cut wait times by 13.9% while CSAT rose 21.2%. Adecco went from prescreening ~10% of candidates to 100%.
Practical deployment guidance on the 5 highest-value use cases: FAQ & policy answers, status/changes/cancellations, scheduling, account support, and triage & routing.

Whether you're just getting started with voice or looking to expand your existing deployment, this is a great read.

Ready to bring voice AI into your agent strategy? Start here 💙

添加评论

撰写评论...

0/9000

今天，04:19

While the summer sun is busy melting the pavement outside, we’ll be inside building ultra-slick, high-performance API-driven experiences with Salesforce Headless 360.

Whether you're sipping iced coffee at home or tuning in from your office AC, this session will give your architecture a serious upgrade.

⏰ When: 8th August at 10:00 AM GST

🔗 Lock in your spot:

https://trailblazercommunitygroups.com/j/wqxw5khm34zw2/

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

添加评论

撰写评论...

0/9000

昨天，13:24

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!

添加评论

撰写评论...

0/9000

7月30日 16:18

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:

Agentforce Coworker - First Look by @David Chater

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!

2 条评论

Joel Primack
8月3日 13:00
Glad it was interesting to you, @Felix Markman 🙌

Hope you had a great weekend!

添加评论

撰写评论...

0/9000

7月28日 13:48

Trailhead Tuesday!

🚀 Agentic AI is evolving — and so are the Agentblazer Status trails!

We've refreshed Champion, Innovator, and Legend with new content to make sure your skills are in step with AI innovation.

Here’s what's new:

⭐️ Champion

AI Fluency Fundamentals: Move from AI awareness to applied fluency in everyday work.

⭐️⭐️ Innovator

Agentforce Grid: Build and link AI prompts to automate end-to-end processes in Agentforce Grid.
Introduction to Salesforce Headless 360: Build on Salesforce any way you want, no browser required.
Headless 360: Use Conversation to Build an Agent and learn how developers—and any Agentblazer—can build with Salesforce Headless 360.

⭐️⭐️⭐️ Legend

Agent Analytics and Monitoring: Discover tools to monitor agent performance and improve its outcomes.
Agentforce Configuration for Slack: Configure an employee agent and deploy it in Slack.

Skill up today 💪

1 条评论

Felix Markman (Promise ROI)
8月3日 01:29
Kudos to Salesforce for creating the Agentblazer program! I recently discovered it, and I’m getting value out of reviewing the modules. These modules are instructional for Salesforce professionals and beyond!

添加评论

撰写评论...

0/9000

7月29日 22:30

When should you build one agent vs. many? And what even is Single-Org Multi-Agent Orchestration (SOMA)?

Jennifer W. Lee breaks it all down in this must-read post for anyone designing Agentforce solutions. ✨

SOMA lets multiple specialized agents work together in one Salesforce org — coordinated by a Super Agent that acts as the unified front door. From the user's perspective, it's one seamless conversation. Behind the scenes, the right agent is handling the right work.

The key question isn't "how many agents can I build?" — it's knowing when a single agent with subagents is enough vs. when your use case calls for SOMA.

A few signals you need SOMA:

Your workflows span multiple domains (HR, IT, Facilities, etc.)
Context overload is causing your agent to misroute or skip guardrails
You need failures isolated so one process crashing doesn't take down the whole experience

And a simple gut check from Jen: if you can't describe a subagent's purpose in one sentence without using the word "and" — it needs to be split further. 💡

Read the full post 🤓

3 条评论

Felix Markman (Promise ROI)
8月3日 01:27
Great post! There is so much attention given to low level work, that high level strategic thinking is less common. This is important for anyone to review.

添加评论

撰写评论...

0/9000

7月30日 04:49

Yalla Habibi! 🚨 Grab your Karak, because the Dubai Trailblazer Community’s favorite duo is officially BACK! ☕✨

Yes, you read that right—whoever was missing Maham, she’s back! The M&M of the Trailblazer Community are reuniting to bring you a hands-on workshop on Salesforce Headless 360 on 8th August

! 💻⚡

BUT... before we hit the lab, you have mandatory prep work. You need to meet my stitched-together co-host, Frankie!

🧟‍♂️🎙️

1️⃣ Step 1: Listen to Frankie & me on Spotify: 👉 https://open.spotify.com/episode/1kbLoZ4pwb6tNs3dNymXDK

2️⃣ Step 2: Lock in your spot for 8th August: 👉

https://trailblazercommunitygroups.com/j/wqxw5khm34zw2/

Don't leave your RSVP to the last minute like Sheikh Zayed Road 6 PM traffic! See you all on August 8th! 🚗💨

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

2 条评论

Misbah ul Iman (DHAM)
7月30日 05:20
Awesome @Aditya Agrawal

添加评论

撰写评论...

0/9000

7月27日 20:12

📣 Extend Data 360 with Code Extension: New Salesforce Developers YouTube Series

Need custom logic that goes beyond Data 360's native capabilities? Our new YouTube series shows you how to build and debug custom Python code locally, then deploy and monitor it in Data 360 using the Data 360 Code Extension SDK and Claude Code. Follow Salesforce Developer Advocate @Alba Rivas as she walks through the complete development workflow, from local development to production.

🔍 In this series, you’ll learn how to:

🔹 Run custom code securely within Data 360

🔹 Build custom Python scripts for batch transforms and custom search index chunking using the Data 360 Code Extension SDK and Claude Code

🔹 Deploy and monitor Data 360 Code Extensions in production

🎥 Watch the full series today: https://sforce.co/4fA1oFo

Want more resources for Salesforce Developers?

Subscribe to the Salesforce Developers YouTube channel
Sign up for the Salesforce Developer newsletter
Follow Salesforce Developers LinkedIn | @SalesforceDevs X

📣 Extend Data 360 with Code Extension: New Salesforce Developers YouTube Series Need custom logic that goes beyond Data 360's native capabilities?

1 条评论

Katie Hobbs (Salesforce)
7月27日 20:15
@Agentblazer Community Group @* Trailhead Official * @Trailblazer Community Cove @Architect Trailblazers

添加评论

撰写评论...

0/9000

7月20日 08:32

Seeking approach ideas — AI-assisted Quote validation against unstructured reference docs (Salesforce/Agentforce)

Hi everyone,

I'm exploring a solution where sales reps receive customer requirements as images, PDFs, Excel files, etc., and manually create Quotes/RFQs in Salesforce. Validation currently depends on 20–25 reference documents (pricing sheets, catalogs, spec sheets) stored on engineers' local machines, which sometimes leads to incorrect quotes.

I'm looking to use Agentforce/AI to:

Identify products/parts from customer documents.
Validate Quotes/RFQs against the customer's original requirements and flag mismatches.
Suggest quote line items automatically.

Constraints:

Prefer a configuration-first approach with minimal custom development.
Quote-related documents are stored as Salesforce attachments/files, so the agent should be able to analyze them during validation on individual opportunities and related RFQs.

Has anyone implemented something similar? I'd love to hear your experience with Agentforce, Data Cloud vector search/RAG, document ingestion, and where you'd draw the line between Salesforce-native capabilities and custom AI solutions.

Also, if you have any recommended articles, blogs, or learning resources on this topic, I'd really appreciate them.

Thanks!

2 个回答

Oleg Mastriukov (Vaneigens)
7月27日 09:09
It sounds like you first need to streamline the process so that customers use a standardized way of sending their requests, then think of any kind of CPQ implementation to sort out the product catalog, and only when it's all done and clean, add AI.