Agentblazer Community Group

[Day 1 of my daily series] Summer '26 drops in 5 days — how are you approaching

Multi-Agent Orchestration?

Hey everyone — first post from me in this community. 

I've been a Salesforce consultant for 10 years, specialised in Sales and Service Cloud

implementations, and I've honestly never contributed much here. I'm fixing that by committing to

share one practical Salesforce insight daily. 

Today's topic: Multi-Agent Orchestration in Agentforce, shipping with Summer '26 on June 15.

The feature is genuinely exciting — agents working together as a team, with shared context, routing,

and escalation built in. The demo use cases look clean. 

But I'm curious how practitioners here are thinking about governance. In my experience, the hardest

part of Agentforce isn't building it — it's owning what happens when it does something unexpected.

Multi-agent adds new dimensions to that problem: 

• How do you audit which agent made a specific decision?

• What happens when Agent A passes incorrect context to Agent B?

• Who owns the escalation path when the whole agent chain fails? 

Are you planning to implement Multi-Agent Orchestration in Summer '26, or waiting to see how it

matures first? 

Would genuinely love to hear how others in the community are approaching this — this is as much a

learning exercise for me as it is a sharing one. First of many posts from me here  

The new Ask Agentforce / Coworker seems excellent.  We've set it up for a pilot group in our org and it seems to be really powerful.  Great UI and should be able to hand-off to other Agents you build.  Makes for a much better AI experience on early testing. 

However, we're unable to fully set it up and as a Beta product it's tricky to get support so wondering if anyone has any recommendations or

if you have any way of passing on contact to the product team. 

Standard search funcitonality seems to work really well.   It can access our org metadata to figure out what a pilot user is asking about, retreive matching records. 

However, when it needs to either query by owner (what tasks do I have due today?) or needs to hand off to an agent users get an error.   

e.g. 'It looks like the current session isn't authorized to access your user details right now — I'm getting an

error, which means the session may have expired or doesn't have API access enabled.' 

I've checked the recommended settings.  I suspect it may be due to us having API Access Controls enabled in our org and there may be an Oauth policy I need to configure but I can't find any documentation to help with this. 

I'd love to be able to use this new Coworker experience before we start extending access and rolling our our agents so any help very much appreciated.

Trailhead Tuesday! 

Everyone starts somewhere with AI. 💙 

The new AI Foundations Trail on Trailhead is built for beginners and makes it easy to kick off your AI journey with hands-on learning, approachable content, and practical skills you can build on over time. 

📊 Data Literacy: Explore, understand, and communicate with data. 

⚙️ Automation Logic: Learn about autonomous workflows. 

⚖️ Responsible AI: remove bias from your data and algorithms. 

✨ Agentforce: A first look at building with autonomous agents. 

Work through real scenarios in your own free Salesforce environment and build a solid foundation before you begin your Agentblazer Journey. 

🆕 Trailhead Quest: Agentic Workflow Automation — Now Live!

Ready to build with AI? The Agentic Workflow Automation Quest is live all month — and we want to see what you create. 

What you'll do:

• Complete the Trailhead trailmix
• Build an agentic workflow using Prompt Builder + Agentforce Grid
• Share your use case via the Google Form

🏆 Enter for a chance to win* 1 of 65 Salesforce certification vouchers. 

🗓️ Deadline: May 31, 2026 

 👉 Start the Quest

*Restrictions apply.  

See Official Rules. http://sfdc.co/bP7smx

RSVP :

Your Salesforce metadata is the DNA of your org. Custom fields, Apex classes, Flows, Validation Rules, Profiles — every piece of configuration tells a story. After 10 years? Some of those stories are concerning. 

In this session we go through the Metadata Lens — identifying what's deployed, what's dead weight, what's dangerous for Agentforce agent actions, and what needs to be cleaned or restructured before you build on top of it. 

What you will learn: 

• The 6 metadata categories that matter most for Agentforce readiness
• How to run Salesforce Code Analyzer for static code analysis — find severity-1 violations before they break your agent actions
• The Safe Deletion Protocol — how to remove unused metadata without causing a 3am production incident
• Why Unlocked Packages are the 2026 standard for metadata organization and how to create your first one
• Apex code quality standards specific to Agent Actions — what must be fixed before your code becomes agent-callable
• How to prioritize technical debt: fix now vs. fix before Agentforce vs. backlog
• Tools Covered: Salesforce Code Analyzer (CLI plugin), OrgCheck , Salesforce CLI metadata commands, Unlocked Package creation

Who Should Attend: Salesforce Architects, Developers, Senior Admins managing legacy org technical debt 

Prerequisites: Session 1 recommended but not required. Basic understanding of Salesforce metadata helpful.