Skip to main content

#Salesforceadmins6 discussing

#Salesforce Developer #Salesforce Admin #Salesforcearchitects #Salesforceadmins #Salesforce_developer #Salesforce #SalesforceArchitect

Know your org better than the admin who left — OrgSage beta is live

Hey everyone,

How many times have you inherited a Salesforce org and had no idea why things were built the way they were? Or hesitated to delete a field because you weren't sure what would break?

We built OrgSage to answer one question: "What happens if I change this?"

OrgSage connects to your Sandbox or Developer Edition org (quick package install + OAuth — metadata only, never your data) and maps every dependency — fields, flows, triggers, validation rules, permissions — so you can understand what you're working with before you touch anything.

A few things it can do:

→ Ask in plain English: "What breaks if I delete Account.Customer_Tier__c?" and get a full impact analysis — which automations, page layouts, and apex classes reference it

→ Cross-org impact analysis: Connect multiple DEV orgs and see how a change in your workstream impacts another team's org — no more surprise conflicts when workstreams merge

→ Detect automation conflicts — when a Flow and an Apex Trigger both write to the same field, see the execution order and which value actually persists

→ Compare orgs — see exactly what differs between DEV, QA, and Production with severity ratings on every change

→ Map relationships and references better than Schema Builder or "Where is this used?"

Try it at getorgsage.com — just connect a sandbox and start exploring.

We're looking for developers and architects willing to try it and share honest feedback — what's useful, what's broken, and what's missing.

0/9000

Who owns it when an AI agent gets it wrong? (A question I keep coming back to.) 

 

We spend a lot of energy on the happy path — the agent qualifies the lead, drafts the reply, updates the record. Far less on the moment it does all of that confidently and incorrectly, maybe in front of a customer. 

 

Agents act in seconds. The human judgment to catch and override them scales in months. That gap seems to be where a lot of rollouts quietly fall apart. 

 

I'm curious how teams here are handling it in practice: 

 

1. Who actually owns or reviews an agent's decisions in your org — RevOps, the line manager, a dedicated "AI steward", or nobody yet? 

2. How fast can a human step in when an agent goes off the rails — and is there a clean rollback? 

 

Not after the vendor answer — genuinely want to hear how Salesforce teams are governing this on the ground. What's working, and what isn't? 

 

#Agentforce #Salesforceadmins

 

 

2 comments
  1. Jun 21, 6:18 PM

    James: The role is defined as the team member focused on leverage Agentforce Observability

    capabilities to monitor and optimize agent interactions. Job description is typically defined as:  

    AI Evaluation Engineer (or LLM Evaluator) - Focus entirely on building frameworks to test, measure, and score AI agents. Trace the exact steps an agent took, review the prompt chain, identify where an agent hallucinated, and score the output for accuracy and relevance. Organizationally, we're seeing this role being an extension of DevOps Teams responsibilities.

0/9000

Summer '26 is live. What's your week-1 plan? 

 

The temptation is to turn on everything at once. After enough release cycles, I've learned the orgs that get value early move in a deliberate order instead. Here's the sequence I'd run: 

 

1. Audit custom Apex for the API v67.0 change first. SOQL/SOSL/DML now default to user mode, and Apex classes default to "with sharing." Legacy code can silently behave differently — fewer records returned, FLS suddenly enforced. This is the one that bites quietly, so I'd check it before turning on anything new. 

 

2. Pilot ONE agent feature, not all of them. Customer Engagement Agent if 24/7 lead follow-up is the gap; Momentum if CRM hygiene is. One feature, configured properly, measured against a baseline. Breadth is how pilots stall. 

 

3. Hold off on Multi-Agent Orchestration. It's GA and it works, but routing depends on how well each agent is described — which only holds up once your individual agents are clean. Month 2-3, not week 1. 

 

Two questions for the community: 

 

1. What's the first Summer '26 feature you're turning on — and why that one? 

2. Has anyone hit the API v67.0 behaviour change in a real org yet? Curious what broke. 

 

#Agentforce #Salesforceadmins

0/9000

Summer '26 is live. First impressions from inside a real org — what's working, what needs attention. 

 

The big headline is Multi-Agent Orchestration reaching GA (Atlas Reasoning Engine 3.0 — dynamic routing between subagents based on their descriptions, no fixed decision trees). It works. But I wouldn't make it Day 1 for most orgs. 

 

Here's what impressed me more on launch day: 

 

The Customer Engagement Agent closes the lead-follow-up gap in a way single agents couldn't. It's 24/7, cross-channel (website + email), and actually converses rather than just deflecting. 

 

Momentum — the conversation capture acquisition from February — is quietly the best addition for sales orgs. Calls, emails, meetings all writing structured data back to Salesforce automatically. If you've ever fought the battle of CRM data hygiene, this is the solution that actually works. 

 

One thing to flag for devs and admins: API v67.0 defaults SOQL, DML, and Database methods to user mode, and defaults Apex classes to "with sharing." Legacy code written for earlier versions can behave unexpectedly. Run the audit if you haven't. 

 

And the Salesforce-hosted MCP servers going GA is the biggest infrastructure play most people are underselling — external AI agents can now call into Salesforce natively. That's the architecture that makes Salesforce the centre of your AI stack. 

 

Two questions for the community: 

 

1. What Summer '26 feature are you turning on first? 

2. Has anyone hit the API v67.0 breaking change yet? 

 

#Agentforce #Salesforceadmins

0/9000

Summer '26 goes live tomorrow. What's the first thing you'll check? 

 

For me it's Multi-Agent Orchestration — specifically how agent handoffs behave in a real org with live data. The sandbox testing was clean, but production always finds something new. 

 

I'm also thinking about the orgs that are going into tomorrow without any prep. No sandbox testing, no checklist, no governance model for Agentforce. We've talked about this all week — the release itself is solid, but autonomous agents on an unprepared org is where the friction comes from. 

 

Two questions for the community: 

 

1. What's the first Summer '26 feature you're testing tomorrow? 

2. Is your org ready, or are you figuring it out as you go? 

 

No judgement on the second one — being honest about where you are is better than pretending you're ready when you're not. 

 

Full first-impressions breakdown incoming tomorrow once I've had time inside a live org. 

 

#Agentforce #Salesforceadmins

0/9000

Salesforce Summer '26 ships 50+ pre-built AI agents for IT service management. 

 

How many of those are you planning to actually deploy? 

 

I've been thinking about the IT Service Domain Pack this week. The concept is strong — agents handling password resets, software requests, and hardware provisioning without Level 1 tickets. That frees up IT staff for work that actually needs human judgement. 

 

But "out of the box" still requires connecting each agent to your systems, mapping your workflows, and doing proper change management. That's not a dealbreaker — it's just the realistic scope. 

 

My question for the community: 

 

For those planning to adopt the IT Service Domain Pack — what's your approach? 

 

→ Pilot with 2-3 agents, validate, then expand? 

→ Go broad from day one and configure in parallel? 

→ Wait and see how early adopters find it? 

 

And is there a specific IT workflow you're hoping one of those 50 agents covers? Curious what the actual demand looks like from practitioners. 

 

#Agentforce #Salesforceadmins

0/9000

Hey #AwesomeAdmin,

I recently completed the Agentforce for Admins module on Trailhead. I found it very useful, especially the ability to perform admin tasks using simple natural language prompts. It's great to see how AI can simplify Salesforce administration and improve productivity.

#Agentforce #Trailhead Challenges #Salesforceadmins

1 comment
0/9000

 

Join us for our upcoming session:

MeshMesh Agents: Operate Salesforce By Simply Asking with David DeVore, founder of MeshMesh.

 

When: Thursday, April 9

Time: 12:00 PM to 1:30 PM EDT

Where: Zoom

 

MeshMesh Agents let you implement and operate Salesforce by simply asking, helping Salesforce Admins and Technical Architects reduce the time required by 80–95%.

 

In this live walkthrough, we explore MeshMesh — the AI platform that enables Salesforce Admins and business users to build, configure, and operate Salesforce by describing the outcome they need. We demo a real task against a live org, cover real-world use cases, and go hands-on with MeshMesh agents, brand kits, workspaces, and references.

 

David DeVore is the founder of MeshMesh, an AI platform focused on helping Salesforce Admins and business users implement and operate Salesforce by describing the outcome they need. He brings more than 20 years of experience across SaaS, product design, and technical architecture.

 

Thank you, David, for joining us.

 

Linkedin Event: https://www.linkedin.com/events/7444024331254284288/?viewAsMember=true

 

Zoom Link:

https://us06web.zoom.us/j/81638545556?pwd=FXEd3zLmAnh2KPt68mz3uVw03xRQp1.1

 

#Salesforce #AI #Salesforceadmins  #Automation  #CodeWithSally

 

Join us for our upcoming session: MeshMesh Agents: Operate Salesforce By Simply Asking with David DeVore, founder of MeshMesh.

 

 

0/9000
On account records in LEX, we have the Details tab as the default tab. This works for most users, but we have certain groups of usere where it would be a great efficiency increase if, for them, the account record defaulted to the Related tab. The documentation is not very concise on any of this. Can anyone distill this down to a short set of bullet points on what to do here?
3 answers
  1. Mar 13, 10:19 PM

    The OP is asking about setting the default tab by User or Profile, NOT cloning and assigning a whole new Lightning record page to manage for every single set of users!  This is the Salesforce administrative nightmare / disaster we're already stuck with and defeats much of the purpose of using Dynamic Forms / Lighting Record Pages over Classic layouts to begin with. Another huge gap with Dynamic Forms from Salesforce (4+ years and waiting).  What good is trying to use Dynamic Forms if you still have to default everyone to the same tab OR are still stuck with "layout sprawl" cloning pages just to land Sales on the Sales tab, Marketing on the Marketing tab, etc.?  

     

    Please upvote this on the IdeaExchange and let's hope it gets some attention by Salesforce so we can actually start using Dynamic Forms in any meaningful way to cut down on page layouts.  

     

    https://ideas.salesforce.com/s/idea/a0B8W00000QcmJaUAJ/customizable-default-landing-tab-for-record-page-tab-set

     

    #Salesforce #Salesforceadmins #Dynamic Forms

      

    @Cheryl Feldman

0/9000

Hello Trailblazers

 

I am trying to solve superbadge - Flow Interactions Superbadge Unit.

I am stuck with challenge 2:

 

Case 5623: Flow Interactions with Assignment Rules and Custom Metadata

Configure a flow to interact with custom metadata to update lead records and trigger existing assignment rules. 

I facing below issue:

 

Challenge Not yet complete... here's what's wrong:

The assignment rule will be executed before the 'Set Lead Region' flow sets the value of the Region field.

 

Solution:

1. I have flow which updates region based on condition

2. I have another flow which executes lead assignment after 1 minute.

 

The solution is working but not sure why trailhead is showing error.

 

Thank you in advance.

 

#𝚂𝚊𝚕𝚎𝚜𝚏𝚘𝚛𝚌𝚎𝙰𝚍𝚖𝚒x

5 comments
  1. Mar 9, 2025, 5:17 AM

    Thank you @Mausam Padhiyar, that worked, @Bethania Soutullo,  Create a new org for it and ensure the Flow is optimized for fast field updates. I was using the same org I used for other superbadge units in the the Flow Management Specialist Superbadge, and was getting that error. However, when I created a new org, the challenge passed for the same steps I had been following for days. As Mausam mentioned, it’s probably a glitch. 

0/9000