[ Salesforce / Data quality ]

Salesforce data that stays clean

engini checks new Salesforce accounts, contacts and leads as they arrive, fixes formatting and missing fields from your own source of truth, and links records that belong together. A weekly agent finds likely duplicates across the org and lists them for a person, who merges in Salesforce. Reports start from clean data instead of a cleanup sprint.

SalesforceNetSuiteSnowflakeGoogle SheetsSlack
Read the Salesforce guide →
A messy new account
  1. Salesforce logo
    Account createdreal-time outbound message
  2. Agent normalizes itname, website, country, industry
  3. NetSuite logo
    Checked against the ERPcustomer list as the source of truth
  4. Slack logo
    Possible duplicate flaggedsame domain as an existing account
Illustration of the flow on this page, not a product screen.
What it does
Normalizes new records, fills gaps, lists likely duplicates for review
Systems
Salesforce, your ERP or warehouse as the source of truth, Slack or Sheets
Built with
A trigger workflow and a weekly scheduled agent
Your control
Merges stay with a person; no delete tools
[ 01 / The problem ]

Every report starts with a cleanup

Blurred landscape photo with the words Data cleanup and the labels Arrive, Fix, Link, Review

Salesforce data degrades quietly: leads imported with inconsistent country names, accounts created twice from different spellings, contacts attached to the wrong account, fields nobody fills. The result is routing that misfires, forecasts split across duplicates and reports that need a manual pass before anyone trusts them.

Where Salesforce data goes wrong

  • Imports and web forms with inconsistent formatting.
  • The same company created from different domains or spellings.
  • Accounts that disagree with the customer list in the ERP.
  • Cleanup projects that start over every quarter.

Fix what is safe, flag what is not

engini catches new records as they are created, in real time through Salesforce outbound messages or every 15 minutes with a record trigger. An AI agent step fixes formatting, fills missing fields from your ERP customer list or data warehouse, and links contacts to the right account. Once a week, a scheduled agent reads the org, groups likely duplicates with its reasons, and writes them to a review sheet or a Slack thread. A person merges in Salesforce; the agent has update tools and no delete tools.

[ 02 / How it works ]

Clean on arrival, reviewed every week

01 / Arrive

New records caught

A Salesforce outbound message, or a record trigger checked as often as every 15 minutes, starts the cleanup workflow.

02 / Fix

Normalize and enrich

An AI agent step fixes formatting and fills missing fields from your ERP or warehouse, with update calls only.

03 / Link

Right account

It links contacts and leads to the right account by domain and your rules.

04 / Review

Duplicates to a person

A weekly agent groups likely duplicates with its reasons in a review sheet or Slack thread. People merge in Salesforce.

This is the flow you will build. Start free and connect your systems.

[ 03 / What the agent reads and writes ]

What the agent reads and writes

Leave delete out of the toolset. The agent updates and links; it does not merge or delete.

SystemRecordsAccess
SalesforceAccounts, contacts, leadsReadUpdate
NetSuite, Snowflake or a databaseCustomer list and firmographics as the source of truthRead
Google Sheets or SlackDuplicate groups for reviewWrite

Connect these systems in engini and give the agent only these tools.

[ 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 thin line, labeled no automatic merge: new record, normalized, duplicates to review

Editorial image: duplicates found, people decide.

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: every Sunday at 20:00, read Salesforce accounts created or updated in the last 7 days, find groups that look like the same company (same website domain or very similar name), and add each group with the reason to the "Salesforce duplicate review" Google Sheet. Do not merge or delete anything.
  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

How do we keep Salesforce clean without quarterly cleanups?

Clean new records as they arrive with a trigger workflow, and let a weekly agent list likely duplicates across the org for review.

Will it merge records automatically?

No. The agent lists duplicate groups with its reasons for a person, who merges in Salesforce. Its toolset has update tools and no delete tools.

Where does the correct data come from?

From the source of truth you choose: your ERP customer list, your data warehouse or a database engini can read.

Does it respect our Salesforce permissions?

Yes. engini acts with the permissions of the connected Salesforce account, so field-level security and sharing rules still apply.