CRM
Agent-driven Intercom topic enrichment across the whole HubSpot book
A Paperclip agent works through every HubSpot contact lacking topic context, gathers each one's Intercom history, reasons about the recurring themes.
How it runs
The automated pipeline, trigger to output.
- TriggerOperator starts the run for a target segment
- ActionFetch HubSpot contacts lacking topic contextHubSpot
- ActionRetrieve each contact's Intercom historyIntercom
- LogicAgent decides if signal is sufficient
- ActionSynthesize narrative and tags with OpenAI reasoningOpenAI
- OutputWrite summary and structured tags to HubSpotHubSpot
What it does
Where the deterministic backfill applies one label per contact, this agent produces richer per-contact context. It iterates the full HubSpot book, and for each under-enriched contact it pulls Intercom history, reasons about what the relationship is really about across multiple conversations, and writes both a short narrative summary and a normalized set of topic tags. It self-corrects when conversations are sparse or contradictory.
When to use it
Choose this for a high-value backfill where a flat single-topic label is too thin, such as enriching strategic accounts ahead of QBRs, or when topics evolve over a long relationship.
How it works
An operator starts the run manually with a target segment. The agent fetches the HubSpot contact list, then loops: for each contact it retrieves Intercom conversations, decides whether there is enough signal, and uses OpenAI reasoning to synthesize a narrative plus tags. A logic step lets the agent skip or defer contacts with insufficient history. The agent writes the summary and structured tags back to the HubSpot contact, then continues until the segment is exhausted.
Set it up
What you configure once, before turning it on.
- 1Connect HubSpotCRM, deals, marketing, support.
- 2Connect IntercomConversations, contacts, articles.
- 3Connect OpenAIModels, embeddings, files.
- 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.