You will learn a staged way to grant an AI agent access to Opportunity data: read first, then propose tasks, then write a few fields.
Why read this
You will also see how the staging exposes data gaps and undocumented exceptions before any record changes.
Level 1: read Opportunity and activities
Level 2: propose Tasks for the owner
Level 3: write a few fields
The agent gains write access only after each lower level works
The author describes an AI agent that reviews Salesforce Opportunities with no activity for 30 days, checks recent interactions and prepares follow-up actions. The design question is what the agent is allowed to do, and the author splits this into three permission levels that the agent moves through only once the level below works.
At level 1 the agent only reads Opportunity, its activities and OpportunityHistory. It runs under its own integration user with a Permission Set limited to the objects and fields it needs, and any tool layer such as MCP exposes read tools only. Every query is logged with its filter. This level shows whether no movement is defined well, since LastActivityDate, stage changes in OpportunityHistory and LastModifiedDate give different lists, and LastModifiedDate also moves when a Flow, integration or bulk load touches a record.
At level 2 the agent proposes rather than edits, creating a Task for the Opportunity owner with the suggested next step, WhatId set to the Opportunity, OwnerId set to the owner and a subject prefix that marks it as agent-written. A person decides what happens. This level reveals exceptions, such as deals deliberately paused, which the agent cannot know unless they are stored in a field, and data gaps, such as calls logged outside Salesforce. The author suggests counting open Opportunities with no LastActivityDate and fixing the data before moving on.
At level 3 the agent writes a few fields, such as a next step or follow-up date, with field-level security keeping the rest read-only. Exceptions are encoded in the query, for example skipping records with a future resume date, and changes are tested in a sandbox with realistic data. Because the agent has its own user, LastModifiedById and field history separate its changes from people’s. The author’s point is that a wrong filter at level 3 corrupts every matching record at once, so the staging keeps mistakes cheap.
You will know how the Sales Cloud in Claude plugin reaches Salesforce, why user permissions set what Claude can read, and how the Dispatch tool restriction setting controls whether Claude can create or update records.
Why read this
You will also have a staged rollout plan with a pre-pilot permission review.
Review permissions before the pilot
Set Dispatch to Deny for read-only
Move to Needs Approval for writes
Use Always Allowed only as last step
Salesforce recommends stepping from read-only to approval-gated writes in this order
Sales Cloud in Claude gives sellers a sanctioned way to ask Claude about their Salesforce accounts. The connection runs as the seller, using their own permissions, against live Salesforce data. The Sales Cloud in Claude plugin, built by Salesforce and Anthropic, bundles 37 sales skills, the Salesforce MCP connection and a setup skill that tailors the plugin to each user’s role. The plugin is in beta and requires an enterprise agreement with Anthropic and Sales Cloud licenses.
The plugin works through the standard Salesforce Hosted MCP Server, which exposes Discover, Describe, Dispatch read-only and Dispatch tools. A Salesforce Admin sets up the server and an External Client App, and the Claude admin configures the connector, sets tool restrictions and decides who gets access. When a seller signs in through OAuth, requests run with that user’s credentials, so field-level security and Sharing Rules apply. Reads need no approval, while writes depend on the Dispatch setting.
Because the hosted server has no generic system user, a user’s object permissions, field-level security and Sharing Rules define what Claude can reach. Those permissions were designed for a human, so broad grants such as View All and Modify All may give Claude more than the job needs. Data Claude reads is also sent to the connected model, which makes the review a data-sharing decision as well as a security one.
The Dispatch tool restriction, found under Organization Settings > Connectors, has three options: Needs Approval, which Salesforce recommends as the steady state; Always Allowed; and Deny, which keeps Salesforce read-only. Dispatch can also call deletes directly even though no skill deletes, so Deny or Needs Approval matters. Salesforce suggests a staged approach: clean up permissions before a pilot, agree the Dispatch setting with the Claude admin, then pilot with a small group and review early approvals. Record each decision in an architectural decision record.
The reader will learn what Agentforce Coworker does, how to find out whether it is already enabled in their org, and why sharing and permissions should be reviewed before rollout.
Check whether Coworker is already on
Review sharing and fix over-broad access
Build a few focused agents
Tell users what Coworker can do
A suggested order for rolling out Agentforce Coworker in an org
Agentforce Coworker is described as Salesforce’s AI assistant for employees, sitting in the search bar and routing user requests to specialist agents. Without well-built agents it can still answer questions from org data but can do little else. The article says it reached general availability at Dreamforce and that more than 185,000 people use it.
The article notes that from August 10, 2026, Salesforce automatically turned on Coworker for customers with unmetered user-based AI seats, which can be checked under Setup, Agentforce Coworker. HIPAA, health and life sciences, and government orgs were not auto-enabled, and Coworker is not covered by the HIPAA Business Associate Addendum. Pricing is said to depend on contract terms.
The main warning is that Coworker respects each user’s existing permissions and Sharing Rules, so it will surface any over-broad access quickly. The suggested rollout is to check the enablement setting, review sharing first, build a few focused agents for common requests such as renewal risk and case status, and tell users what the assistant can and cannot do.
By Joshua Dreiling · Salesforce ArchitectsThe piece also explains when to use functional versus persona-based Permission Sets and why Profiles should be kept minimal.
You will learn how to map business personas to a User Field, a Custom Metadata Type, a Permission Set Group and Apex automation, so access stays consistent as features are added.
Why read this
The piece also explains when to use functional versus persona-based Permission Sets and why Profiles should be kept minimal.
Persona set on User record
Custom Metadata Type maps persona
Permission Set Group for persona
Permission Sets grant access
Apex assigns access on save
How a persona assigns a user's access, from the User record through to Apex
The article argues that Salesforce security models often become a fragmented patchwork, and that features can fail on release because users lack the access they need. Its remedy is to build the security model around personas: groups of users who share a functional role and baseline access. The business defines which persona needs which access (create, read, edit, delete) for a feature, and IT implements that access consistently, so the same framework can serve later releases. Shared understanding between IT and the business is treated as essential to making this work.
The approach rests on five pieces. A persona picklist on the User record, whose edits are tightly restricted to administrators, stores each user’s persona. A Custom Metadata Type acts as a maintainable mapping table from each persona to its profile, role, public groups and Permission Set Group, and automation fails if a persona lacks a mapping record. Each persona gets one Permission Set Group, which has no access of its own, so changing a persona’s access means changing its Permission Sets. Those Permission Sets can be organized either by functional capability, which suits features spanning many objects such as Field Service, or by persona, which suits cases with few personas and complex functions, such as a Partner Relationship Management Experience Cloud site. Temporary cross-role duties are handled through an approved exception process, such as an ITSM workflow, while permanent combined roles should become new personas.
The article also recommends keeping profiles minimal: each user gets a custom “Minimum Access” profile, one per license type, with most permissions moved to Permission Sets, since profiles are still needed only for edge cases such as page layouts, login hours and IP ranges. Assignment is automated with Apex through the organization’s trigger framework, which the author prefers over Flows for consistent performance at scale. For teams not ready for the full design, the author suggests starting with Permission Set Groups for the personas a feature and its successors will need, assigned manually at first, and adding the persona field and automation later. The article frames this as a way to meet the Salesforce Well-Architected Framework’s goals of scalability and predictability.
You will learn what each of Record Types, Profiles and Permission Sets is for, and how to decide which one fits a given requirement.
Why read this
The article also explains why Record Types are not a security control.
Record Type
Different business processes
Controls picklist values per process
Not a security control
Permission Set
Grants additional access
Assigned to selected users
Field and object permissions
Each tool solves a different problem, so match the requirement to the right one
This Salesforce Ben article helps admins decide between Record Types, Profiles and Permission Sets when a new requirement arrives. It explains that Record Types support different business processes for the same object, controlling available picklist values through Sales Processes and working with Page Layouts. It stresses that Record Types are not a security mechanism, since assigning one does not govern which records or fields a user can see or edit, and that restricting Record Types does not block access to existing records using other types.
Profiles, which every user has exactly one of, are described as the baseline for a user’s experience, covering login hours, IP ranges, password and session settings, default apps, default Record Types and Page Layouts. Permission Sets add access on top of that baseline, and a user can hold several of them; Permission Set Groups bundle commonly paired sets together. The article notes Permission Sets generally grant rather than remove access, and that a muting Permission Set inside a group only suppresses permissions from other sets in that same group, not those from the Profile or outside the group.
A decision table maps requirements to starting tools, and the article warns that one requirement may need several tools working together. It walks through worked examples: sales-process picklists suit Record Types, a handful of users needing a feature suits a Permission Set, and hiding fields from a Page Layout does not secure them, so field-level security is needed. It closes with five anti-patterns to avoid, including creating a Profile per department, using Record Types for security, duplicating Profiles in Permission Sets, ignoring Record Types in layout design, and letting Permission Sets sprawl, along with a set of questions to ask before configuring. The article also notes that Salesforce’s retirement of Profile-based permissions was cancelled in June 2026, while it still recommends a permission-set-led approach.
You will learn the five checks to run when an Agentforce Service Agent fails with a field-access error while answering from Knowledge articles, and the order to run them in.
Why read this
The piece is a practical troubleshooting guide rather than new platform news.
Assign Data Cloud User Permission Set
Grant Read on Knowledge and mapped fields
Enable Allow View Knowledge
Verify data space access
Confirm search index is Ready
The five checks to run in order when the field-access error appears
The article covers an error that appears when the Answer Questions with Knowledge action runs against an Agentforce data library: the agent’s running user cannot read one or more fields the library depends on. The usual causes are missing permissions, missing field-level security, or an incomplete Data Cloud setup. The agent runs as the user with the Einstein Agent User profile, and every object, field and Data Cloud resource the data library touches must be readable by that user.
The guide gives five checks in order: confirm the Data Cloud User Permission Set is assigned to the agent user, confirm Read access on the Knowledge object and every mapped field, enable Allow View Knowledge, verify the user’s data space access in Agent Studio, and confirm the search index for the Knowledge data library is Ready. It also recommends a dedicated Permission Set for the agent user, re-auditing field-level security whenever the library changes, granting least privilege, and testing as the agent user rather than as an admin.
The author notes that the source material contained no code, and that the link between an unready search index and this specific message is not confirmed in the source, so it should be checked as a separate cause.
You will learn what Salesforce Go is, which editions and permissions it needs, and how Feature Sets, Features and feature monitoring work in its setup dashboard.
Why read this
It is a practical orientation for admins adopting it.
Turn on the feature
Configure the setup steps
Monitor it once completed
Enabling a feature from Salesforce Go follows three stages
Salesforce Go began as Sales Cloud Go to help Sales Cloud admins enable new features, and its scope now covers all Salesforce feature setup. It is found in the Setup menu, and it is available to users with the View Setup and Configuration permission in several editions with Service Cloud. Additional permissions may still be needed depending on the feature being enabled.
The dashboard groups cards into Agents, Features and Feature Sets, and each Feature Set bundles the features that work toward one outcome, such as the Capture & Auto-Qualify Leads set. Each feature links to Salesforce Help, and includes snapshots, videos and a Copy Details option for sharing with stakeholders. The author walks through turning on Sales Engagement from the dashboard, then configuring access with a Manage button or a Go to Setup button where the task lies elsewhere.
Once a feature is marked Completed, Salesforce Go can also be used to monitor it, manage its configuration, assign permissions and track license consumption where applicable.
You will learn what Quick Pages does, how its Permission Sets and read-only beta limits affect your org, and what is planned next.
Why read this
Useful if you plan to let users build their own views.
Describe the page in natural language
Review a live preview as it is built
Share with individuals, groups or the org
How a user builds and shares a Quick Page in the beta
Quick Pages, now in beta, lets users in an org build and share their own single-page apps with charts, data tables, tabs and actions, described in natural language through Agentforce Coworker or the Quick Pages tab. The pages are grounded in the org’s metadata, including Custom Objects and fields, and show a live preview while they are built.
The pages follow the standard Salesforce security model, so users see only the data they can access, and they pull from live data rather than going stale. Building a page does not change the org’s metadata. Admins control access with the “Create and View Quick Pages (Beta)” and “View Quick Pages (Beta)” Permission Sets, and can view and manage every page. The Headless Toolkit applies the same permission checks and data rules whichever client builds the page.
During beta, AI chat is free but will be metered at general availability. Pages built in beta are read-only, so users cannot change records from them yet, and they will remain viewable after general availability. Planned additions include record editing, Apex and Connect REST API data sources, Data 360 support, and a Claude integration.
Readers will learn a structured six-point checklist for evaluating the security, permissions and costs of agents and MCP tools before they reach production.
Why read this
The guide explains how to test these integrations safely and establish ongoing monitoring.
The article outlines the transition of AppExchange to AgentExchange, noting that the marketplace now hosts agents, subagents and MCP servers alongside traditional managed packages. It emphasizes that these newer components operate at runtime rather than just adding static metadata, which changes how administrators must assess their impact.
Authors provide a six-step verification process covering security review status, profile access limits, data flow mapping, agent user permissions, pricing structures using Flex Credits, and publisher reputation. They stress that passed security reviews set a baseline but do not guarantee safe runtime behavior.
The piece recommends a Sandbox evaluation workflow that includes testing under different user states, allowing only necessary MCP tools, enabling logging, and modeling costs at projected volumes. It concludes with operational rules such as enforcing least privilege, requiring weekly transcript reviews during pilots, and defining offboarding procedures before deployment.