Per-pair page

HubSpot + OpenAI: AI inside your CRM.

Use GPT-4o to score HubSpot leads, draft outbound emails, summarize deal activity, or classify tickets. AI on top of HubSpot data without leaving the workflow.

Connect OpenAI and HubSpot See reverse direction

Trigger app

OpenAI as the trigger

Workflows fire when something happens in OpenAI.

OpenAI has no triggers yet. Use the catalog's universal Webhook trigger as the upstream.

Action app

HubSpot as the action

Workflows do something in HubSpot, instantly.

See all 23 actions →

Both directions

Pick the way that fits your stack.

Pair pages are mirrored. Each direction gets its own dedicated page.

OpenAI → HubSpot

When something happens in OpenAI, do it in HubSpot.

0 OpenAI triggers wired to 23 HubSpot actions.

HubSpot → OpenAI

Or fire it the other way around.

18 HubSpot triggers wired to 16 OpenAI actions downstream.

See HubSpot → OpenAI →

How it works

Connect OpenAI and HubSpot in five steps.

No code, no glue, no half-day setup. Each step is one click.

1
Connect
Authorize OpenAI and HubSpot
Open Tiny Command, authorize OpenAI and HubSpot once each. Both connections are available to every workflow on your account.
2
Trigger
Pick a OpenAI trigger
Drop the OpenAI → New event trigger onto the canvas. Tiny Command auto-registers the webhook.
POST /v1/webhooks/openai.event
3
Transform
Add a filter or AI step
Optionally add a Filter node ("subject contains URGENT") or an AI step ("classify intent") between trigger and action.
4
Action
Add the HubSpot action
Drop the HubSpot → Create Company action below it. Map fields from the OpenAI payload into the HubSpot inputs.
hubspot.create-company
5
Publish
Publish and forget
Hit Publish. Tiny Command runs it in production from second one. Watch the run-log fill up.

FAQ

Questions about OpenAI + HubSpot.

How do I AI-score HubSpot leads with GPT?

HubSpot Contact Created → enrich (Clearbit, etc.) → OpenAI Chat returns JSON {score, reasoning, segment} → HubSpot Update Contact with score + reasoning in custom properties. Reps see the why.

Can GPT draft outbound emails from HubSpot contact data?

Yes. Pass name, company, role, recent activity, brand voice examples → GPT returns personalized first-touch email. Create as Gmail draft or as HubSpot sequence enrollment for rep review.

How do I summarize a HubSpot deal's history with GPT?

Fetch deal Engagements (notes, emails, calls) → concatenate → OpenAI Chat summarizes in 5 bullets + flags risks → HubSpot Create Note with the summary. Useful before next account meeting.

Can GPT classify HubSpot tickets by urgency?

Yes. HubSpot Ticket Created → OpenAI classifies priority + intent (bug, billing, account, feature) → HubSpot Update Ticket with property + routing to right queue. Reduces triage delays.

How do I keep GPT responses concise for HubSpot properties?

HubSpot single-line caps at 65,536 chars but UI shows ~200. Constrain GPT with "max 150 chars" + max_tokens. Long-form belongs in deal notes, not properties.

Which OpenAI model for HubSpot enrichment?

gpt-4o-mini for classification, scoring, tagging (very cheap). gpt-4o for nuanced drafting of summaries and outbound. Cap tokens; track per-record cost from response usage.