SyncOnAI360

Salesforce AI Agents

Specialist AI agents for Salesforce, with limits you set.

Pick the right specialist for the job: admin, Flow, Apex, LWC or data. Each has its own instructions and tools, every tool can be allowed, denied or held for confirmation, and every call is recorded.

Try the agents freeBook a demo

SyncOnAI 360

AI architect for Salesforce

Ask SyncOnAI to build flows, rules, Apex, or SOQL...

In one paragraph

SyncOnAI 360 agents are specialist versions of the org-aware chat, each with its own instructions, skills, tools, knowledge and model. The library covers Salesforce admin, Flow and automation, Apex, Lightning Web Components, and SOQL and data work. Agents run on the same chat engine with the same approvals, and every tool call is recorded.

Specialist agents in the library
5Specialist agents in the library
Per-tool settings: allow, deny or confirm
3Per-tool settings: allow, deny or confirm
Tool call recorded
EveryTool call recorded
Memories saved without a person's approval
0Memories saved without a person's approval

01The problem

Why a single general AI assistant struggles with Salesforce work

Salesforce work spans very different jobs: configuring objects, building Flows, writing Apex, building components, answering data questions. One general assistant with every tool and no limits is both less useful and less safe.

  1. 01

    Jack of all trades

    A general assistant gives general answers. Specialist work needs specialist instructions and tools.

  2. 02

    Too much power by default

    An assistant that can do everything can also do the wrong thing, with nothing in between to stop it.

  3. 03

    No visibility

    Teams cannot see which tools an assistant has, or whether a tool writes or only reads.

  4. 04

    Memory nobody approved

    Assistants that remember things on their own pick up wrong conventions and never let go.

02library

Which Salesforce AI agents are available?

The Salesforce Admin agent works on objects, fields, validation rules, layouts, list views and reports. The Flow and Automation agent builds and fixes Flows. The Apex Engineer writes Apex classes, triggers and tests. The LWC Developer builds Lightning Web Components. The SOQL and Data agent answers read-only queries and data questions.

Each agent is built on Salesforce's own published skills, adapted to the tools in SyncOnAI 360, and works from the connected org's metadata and source rather than from a generic picture of Salesforce.

  • Salesforce Admin
  • Flow and Automation
  • Apex Engineer
  • LWC Developer
  • SOQL and Data

SyncOnAI 360

AI architect for Salesforce

Ask SyncOnAI to build flows, rules, Apex, or SOQL...

03permissions

How do you control what a Salesforce AI agent can do?

On the Agents page, each agent shows its tools and whether each one reads or writes. Any tool can be allowed, denied or held for your confirmation, so an agent's reach is a decision rather than a default.

While an agent is active, any change to an org waits for approval and becomes a proposal like any other change, with named checks, blast radius and, for production, a second admin's approval. Every tool call is recorded, and recent runs and their outcomes are listed on the Agents page.

  • Tools listed with read or write
  • Allow, deny or confirm per tool
  • Changes still go through proposals
  • Every call recorded

Proposal: Case intake fault handling

Acme Production

Checks passed

Made by

D. Chen, admin

Cannot approve own production change

Approver

M. Okafor, admin

Policy: production requires an admin other than the author. Recorded on the receipt.

04skills memory

How do agent skills and memory work?

Skills are reusable instructions an agent can load when it needs them. Each skill records where it came from and which version is in use, so behaviour can be traced.

Agents can suggest something worth remembering, such as a naming convention your team uses, but nothing is remembered until a person approves it. Memories belong to a conversation, a project or a person, never cross into another workspace, and can be reviewed in settings.

  • Versioned, traceable skills
  • Memories only with approval
  • Memories never leave the workspace

Knowledge Hub

Documentation, patterns, your orgs and pages

  • [1] Salesforce documentationFault connectors and error handling in Flows
  • [2] Your orgCase_Intake_Route: 2 elements without a fault path
  • [3] DependenciesEscalate_High_Priority runs after it on save
  • [4] PagesRunbook: Service automation standards

05models

Which models do Salesforce agents run on?

The workspace chooses a model for agents separately from the model the chat uses, from Anthropic and OpenAI. When AI is included in the plan, the right model is picked per task: a light model for quick answers, a stronger one for building and the strongest for hard reviews.

Neither provider trains on API traffic. On the Free plan, agents run on your own provider key and account.

  • Separate model for agents and chat
  • Model picked per task when AI is included
  • No training on API traffic

Workspace security

Settings · Security

  • Configuration onlyMetadata and code. CRM records stay in Salesforce.
  • Isolated per customerEnforced by the database and tested every release.
  • Keys in Google Cloud KMSCredentials encrypted under a per-customer key.
  • Second admin for productionThe author can never approve their own change.
  • Hosted in the United StatesEvery subprocessor listed with its region.

06chat

How are agents different from the chat?

The chat is the general assistant. Agents are specialists with their own instructions, skills and tool permissions for one kind of work, such as Flows or Apex. Choose an agent when the job is clearly in its area, and the chat when a question spans several.

Both run on the same engine, read the same org and follow the same approvals, so switching between them never changes what is allowed to reach the org.

  • Specialists for one kind of work
  • One engine and one set of approvals

SyncOnAI 360

AI architect for Salesforce

Ask SyncOnAI to build flows, rules, Apex, or SOQL...

07How it works

Working with an agent

A specialist, inside the same guardrails as everyone else.

  1. 01

    Pick

    Choose the specialist in the chat composer.

  2. 02

    Ask

    Describe the job; the agent works from the org's metadata and source.

  3. 03

    Confirm

    Tools held for confirmation wait for you.

  4. 04

    Review

    Changes arrive as proposals with checks and blast radius.

  5. 05

    Approve

    Production changes need a second admin; every call is on record.

08Before and after

AI assistance, general versus specialist

Without

With SyncOnAI 360

One assistant for every job

Specialists for admin, Flow, Apex, LWC and data

Every tool on by default

Allow, deny or confirm each tool

Unknown read or write power

Each tool labelled read or write

Memory that builds up unchecked

Memories saved only with approval

No record of what it did

Every tool call and run recorded

09Who uses it

Who works with the agents

Salesforce adminsHand routine configuration to the Salesforce Admin agent, objects, fields, validation rules, layouts, list views and reports, and review each change as a proposal before anything reaches the org.Salesforce developersPair with the Apex Engineer and the LWC Developer for classes, triggers, tests and components that follow the org's own patterns, with every tool call recorded.Platform ownersDecide exactly what each agent may do: allow, deny or hold any tool for confirmation, see recent runs, and keep production behind a second admin's approval whatever an agent proposes.ConsultanciesGive every consultant the same specialist agents and approved memories, such as a client's naming conventions, so work stays consistent across the team without crossing between workspaces.

10Questions

Frequently asked questions

A specialist version of the org-aware chat with its own instructions, skills, tools, knowledge and model, for jobs like Flow building, Apex or data questions.

No. Any change an agent makes to an org waits for approval and goes through a proposal with checks; production needs a second admin.

Yes. Each tool can be allowed, denied or held for confirmation.

Yes. Every tool call is recorded, and recent runs and their outcomes are listed on the Agents page.

Only what a person approves. Agents can suggest memories; nothing is saved until approved.

It is for read-only queries and data questions. Data-changing Apex in the chat always waits for an explicit Allow.

Yes. The workspace sets a model for chat and a separate one for agents.

Yes. Every plan includes every feature.

11Keep exploring

Related

AI AgentOrg-aware chat and specialist agentsAI EngineeringAI that knows the connected orgPrompt LibraryVerified Salesforce prompts with org-aware fieldsFlow BuilderFlows from a sentence or the canvasApex BuilderApex as logic or code, with testsPricingEvery feature on every plan

Start in 5 minutes. No card required.

Connect your Salesforce org. Run your first health scan. Ask your first question. See what you've been missing.

Start free, connect my orgBook a demo with SyncOnAI
  • Anthropic
  • OpenAI