CRM
AI agent that resolves duplicate contacts across HubSpot and Salesforce
An agent investigates a flagged contact, gathers all matching records from both HubSpot and Salesforce, reasons about which field values are most trustworthy.
How it runs
The automated pipeline, trigger to output.
- TriggerContact flagged for review via webhookHTTP webhook
- ActionGather candidate records from HubSpotHubSpot
- ActionGather candidate records from SalesforceSalesforce
- LogicReason over conflicting fields for golden record
- ActionWrite reconciled record back to HubSpotHubSpot
- OutputSync reconciled record to SalesforceSalesforce
What it does
Given a contact flagged as a likely duplicate, an agent pulls every related record from both HubSpot and Salesforce, weighs conflicting field values using recency and source reliability, and produces one reconciled golden record that it writes back to both systems.
When to use it
Use this when the same person lives in two CRMs and simple field rules aren't enough — you need judgment about which system's title, phone, or owner to trust. Good for teams running parallel HubSpot (marketing) and Salesforce (sales) instances that drift apart.
How it works
- 1A contact is flagged for review via webhook (from a form, an enrichment tool, or a rep).
- 2The agent fetches all candidate records from HubSpot.
- 3The agent fetches all candidate records from Salesforce.
- 4It reasons field by field, choosing each winning value by recency, completeness, and source authority, and explains its picks.
- 5It updates the surviving HubSpot record and links or merges the duplicates.
- 6It writes the same reconciled values to Salesforce so both systems agree on one truth.
Set it up
What you configure once, before turning it on.
- 1Connect HubSpotCRM, deals, marketing, support.
- 2Connect SalesforceAccounts, opportunities, cases.
- 3Connect HTTP webhookTrigger any URL on agent actions.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More CRM workflows
Dormant Account Check-In Call Scheduler
On the anniversary of an account's last touch, books a tentative check-in call on the owner's Google Calendar and emails the contact a scheduling invite.
Weekly Dormant-Anniversary Cohort Digest
Every week, groups dormant Attio accounts by which last-touch anniversary they hit that week, builds a prioritized digest.
AI-Personalized Dormant Account Win-Back
On a dormancy anniversary, an agent researches the account's history and recent public signals, drafts a genuinely personalized win-back email.
Backfill Intercom conversation topics onto stale HubSpot contacts
Finds HubSpot contacts with no recent Intercom topic, pulls their conversation history from Intercom, classifies the dominant topic with OpenAI.
Daily orphaned-opportunity sweep with manager Slack digest
Each morning this scans Salesforce for open opportunities owned by inactive users and posts a per-manager digest in Slack listing the orphaned deals that need a new owner.
Tag closed Intercom conversations onto Salesforce contacts in real time
On each Intercom conversation close, classifies the topic with OpenAI and appends it to the matching Salesforce contact's activity timeline so the topic never goes stale…
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.