[ Salesforce / Service ]

Salesforce cases, triaged as they arrive

When a case is created, engini starts a workflow in real time. An AI agent reads the case and its attachments, classifies and prioritizes it, looks up the customer’s order or invoice in the ERP when that matters, sets the owner and drafts a reply. Bugs become Jira issues, and the Jira status comes back to the case.

SalesforceJiraNetSuiteSlack
Read the Salesforce guide →
A case about a late order
  1. Salesforce logo
    Case created from emailreal-time outbound message
  2. Agent reads and classifiestype: delivery; priority: high
  3. NetSuite logo
    Order status checkedSO-10422 shipped yesterday
  4. Salesforce logo
    Owner and fields setlogistics queue; draft reply saved
Illustration of the flow on this page, not a product screen.
What it does
Classifies, prioritizes and routes cases with ERP context; escalates bugs
Systems
Salesforce, NetSuite or SAP S/4HANA, Jira, Slack or Teams
Built with
A workflow on a real-time Salesforce trigger with an AI agent step
Your control
Replies are drafted for an agent to send, unless you decide otherwise
[ 01 / The problem ]

Triage eats the time meant for solving

Salesforce itself puts it plainly: manual triage takes time and effort, human error lets high-priority tickets get ignored, and support agents spend time tagging cases instead of solving them (Salesforce). Its own fix depends on editions many teams do not have.

Many cases also need information that is not in Salesforce at all. "Where is my order" and "why was I charged twice" are answered in the ERP, so the agent opens another system, finds the order, and comes back.

Where support time goes

  • Reading every new case to decide type, priority and queue.
  • Opening attachments to understand what the customer sent.
  • Looking up orders and invoices in NetSuite or SAP.
  • Copying bugs into Jira and checking back for status.

Triage by an agent, with the context attached

engini receives the outbound message as soon as the case is created. An AI agent step reads the case and downloads its attachments, decides the type and priority from the content, and, when the case is about an order or an invoice, reads the status from NetSuite or SAP S/4HANA. It sets the fields and owner and saves a drafted reply on the case for your support agent.

When the case is a bug, the agent creates a Jira issue with the case details, and the Jira key and status flow back to the case. Teams that also run Zendesk can mirror tickets the same way.

[ 02 / How it works ]

Read, classify, check, route

01 / Trigger

Case created

A Salesforce outbound message starts the workflow in real time when a case is created.

02 / Read

Understand the case

An AI agent step reads the case and its attachments and decides type and priority from the content.

03 / Context

Check the ERP

For order and billing cases it reads the order or invoice status from NetSuite or SAP S/4HANA and adds it to the case.

04 / Route

Owner, draft, escalation

It sets fields and owner, saves a drafted reply, and creates a Jira issue for bugs, with Jira status synced back to the case.

[ 03 / What the agent reads and writes ]

What the agent reads and writes

SystemRecordsAccess
SalesforceCase, Contact, Account; case attachmentsReadDownload
SalesforceCase type, priority, owner, drafted reply, Jira keyUpdate
NetSuite or SAP S/4HANASales order and invoice statusRead
JiraIssues for bugs; status read backCreateRead
Slack or TeamsAlerts for urgent casesWrite
[ 04 / Build it with the engini skill ]

Describe it in plain words. The engini skill builds the workflow.

engini skills is engini’s plugin for Claude Code and Codex. Its workflow agent, Flo, turns a plain-language request into an engini workflow: it designs the steps, dry-runs them against your own engini account, shows you a proposal, and creates the workflow only after you approve it, always turned off. You check it in the engini designer and turn it on.

Blurred landscape photo with the Salesforce logo, the engini mark and a frosted tile joined by a thin line, labeled triaged: case, order status, owner

Editorial image: each case, its own track.

Claude Code: install once
/plugin marketplace add engini/skills
/plugin install skills@engini
Then ask for this solution
Build a workflow in my engini account: when a Salesforce case is created, classify it as billing, delivery, bug or other and set its priority from the description; for delivery cases, read the related sales order status from NetSuite and add it to the case description; for bugs, create a Jira issue in project SUP with the case subject and description and write the Jira key to the case.
  1. You need an engini account, the engini CLI (npm i -g @engini/cli) and a workspace-scoped API key, ideally a dedicated least-privilege one.
  2. Connect the systems this flow uses in engini first. Flo never creates or changes a connection and never handles your key; it tells you which command to run.
  3. Flo checks your login and workspace, searches the tool catalog, compiles the plan and shows a proposal table with every step. It creates the workflow only when you approve that proposal, and it creates it turned off.
  4. Open it in the engini designer, fill anything it left for you, and turn it on.
engini skills for Claude Code and Codex →
What the skill will never do on its own →
[ 05 / Agent Policy ]

The agent does only what you allow. Every run is on the record.

Agent Policy is how you govern agents in engini: the tools each agent may call, the account each tool uses, and a record of every call.

Toolsets

Scope every call

Hand the agent a toolset: only the tools it needs, each on the connection you choose, for example read only. engini enforces it on the server for CLI, SDK and REST API calls; a call outside the toolset is refused. An MCP server exposes only the connections and tools chosen when you set it up.

Identity

Acts with the account you connect

engini acts with the permissions of the connected account. Connect a person’s own account and it acts as that person; use a shared integration account and it acts as that account. Every run is recorded under the user who triggered it.

Audit

History and audit log

Each tool call and workflow run is recorded in History and the audit log, which supports export and streaming to your SIEM. Your agent never needs your credentials: engini stores them and adds them when it runs each call.

SOC 2 Type IIISO 27001GDPRHIPAA compliant
[ 06 / Try it now ]

Build it on your own data today

Start free, connect Salesforce, and build this flow with the engini skill, in Workflow Studio, or from your own agent.

  • 01Workflow Studio. Build the flow on a visual canvas, with an AI agent step where judgment is needed. Start free →
  • 02Your own agent. Give Claude, ChatGPT or Cursor an engini MCP server with only these tools. MCP client setup →
  • 03The engini skill. Ask Flo in Claude Code or Codex and review its proposal. Install the skill →
[ 07 / Questions ]

Questions buyers ask before they start

Can AI triage and route Salesforce cases without Einstein?

Yes. An engini workflow on a real-time outbound message reads each new case with an AI agent step and sets type, priority and owner through the Salesforce connection.

Can it look up order or invoice status in the ERP?

Yes. For order and billing cases the agent reads the status from NetSuite or SAP S/4HANA and adds it to the case, so the support agent does not have to switch systems.

Can cases be escalated to Jira with status synced back?

Yes. Bugs become Jira issues with the case details, and the Jira key and status are written back to the case.

Does it reply to customers on its own?

Only if you build it to. The usual setup saves a drafted reply on the case for your support agent to review and send.

How is this different from Agentforce for Service?

Agentforce works inside Salesforce. engini lets an agent use Salesforce, your ERP and Jira together, and you change its rules in plain language in Workflow Studio.