[ Salesforce / Lead routing ]

Salesforce lead routing that reads the lead

The moment a lead lands in Salesforce, engini starts a workflow in real time. An AI agent checks whether the company is already an account, enriches the lead from your own data, scores it against your ideal customer, sets the owner and alerts the rep in Slack or Teams with a drafted first email. Leads nobody touched get reassigned on a schedule.

SalesforceSlackSnowflakeOutlook or Gmail
Read the Salesforce guide →
A demo request at 4:52 pm
  1. Salesforce logo
    Lead createdreal-time outbound message
  2. Agent matches and enrichesexisting account found; size and region from your data
  3. Scored against your ICPfits: mid-market, NetSuite user
  4. Salesforce logo
    Owner setaccount owner keeps the relationship
  5. Slack logo
    Rep alerted with a draftDM with context and a first email
Illustration of the flow on this page, not a product screen.
What it does
Real-time match, enrich, score and assign for every new lead
Systems
Salesforce, your data warehouse or database, Slack or Teams
Built with
A workflow on a real-time Salesforce trigger with an AI agent step
Your control
Your scoring rules, your territories, your SLA
[ 01 / The problem ]

Slow follow-up is usually a routing problem

Everyone agrees that speed to lead matters. What slows it down is rarely the rep. It is the minutes or hours spent figuring out who should get the lead: is this company already a customer, which territory is it in, is it worth a call today. LeanData reports a customer cutting routing time in half and lifting lead-to-opportunity conversion as a result. Salesforce’s built-in assignment rules are static, as SalesforceBen explains, so anything that needs judgment falls back to a person.

Where routing goes wrong

  • A lead from an existing account goes to a new rep instead of the account owner.
  • Leads are scored on form fields, not on what you know about the company.
  • The rep gets an email notification and no context.
  • Nobody notices a lead was never worked.

Routing with judgment, in real time

engini receives Salesforce’s outbound message the moment the lead is created. An AI agent step looks the company up among your accounts, pulls what you already know from your data warehouse or database, applies your scoring rules in plain language, and sets the owner and rating on the lead. The rep gets a Slack or Teams message with who the lead is, why it scored that way and a drafted first email.

A scheduled workflow closes the loop: leads still untouched after your SLA are reassigned and the manager is told.

[ 02 / How it works ]

Every lead, routed in one pass

01 / Trigger

Lead created

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

02 / Match

Account and context

An AI agent step matches the lead to an existing account by domain and name, and enriches it from your warehouse or database.

03 / Assign

Score and owner

It scores the lead against your rules, sets the owner and rating on the lead, and keeps existing accounts with their owner.

04 / Alert

Rep and SLA

The owner gets a Slack or Teams message with context and a drafted first email. A scheduled check reassigns leads untouched after your SLA.

[ 03 / What the agent reads and writes ]

What the agent reads and writes

SystemRecordsAccess
SalesforceLead, Account, Contact, UserRead
SalesforceLead owner, rating and routing notesUpdate
Snowflake, Databricks or a databaseFirmographics and product usage you already holdRead
Slack or TeamsAlerts and drafted first emails to the ownerWrite
[ 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 real time: lead, match + score, owner

Editorial image: one lead, the right route.

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 lead is created in Salesforce, look for an existing account with the same email domain; if one exists, set the lead owner to the account owner, otherwise assign by the lead's country using this rule: US and Canada to Dana, everyone else to Lior. Then send the new owner a Slack message with the lead's name, company and a drafted first email.
  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 route Salesforce leads faster than assignment rules?

Start routing from a real-time outbound message, so the workflow runs the moment the lead is created, and let an AI agent step make the judgment calls assignment rules cannot: account matching, enrichment and scoring.

Can an AI agent match a lead to an existing account?

Yes. It searches your Salesforce accounts by email domain and company name and keeps the lead with the account owner when it finds one.

Where does enrichment data come from?

From data you already hold: your data warehouse, a database or a spreadsheet engini can read. engini does not sell or supply third-party data.

What happens when a lead is not worked in time?

A scheduled workflow finds leads still untouched after your SLA, reassigns them by your rule and tells the manager in Slack or Teams.

How is this different from LeanData or Distribution Engine?

Those are dedicated routing tools inside Salesforce. engini routes with an AI agent that can read your other systems and act in them too, and you change the rules in plain language in Workflow Studio.