Automate HubSpot + YouTube
The CRM your pipeline reporting depends on. Long-form content worth repurposing everywhere else. Put an agent between them and the hand-off stops being manual: it reads, decides, acts, and shows its work.
Lead Researcher is a ready-made agent built around HubSpot; point its last step at YouTube to finish this hand-off.
Automations teams run
Unlike field-mapping automation, the step in the middle is an agent: it can summarise, classify, judge and draft, not merely copy values from HubSpot into YouTube.
When a contact or deal is created in HubSpot…
…an agent can pull transcripts and stats in YouTube — after reading the context and deciding it should.
When a stage changes in HubSpot…
…an agent can draft descriptions and chapters in YouTube — after reading the context and deciding it should.
When a form submits in HubSpot…
…an agent can summarise comments in YouTube — after reading the context and deciding it should.
When a video is published in YouTube…
…an agent can create and enrich contacts in HubSpot — with the reasoning recorded in the run’s receipt.
When a comment arrives in YouTube…
…an agent can update deals and notes in HubSpot — with the reasoning recorded in the run’s receipt.
The HubSpot and YouTube hand-off, in full
The two ends are a custom-api call to api.hubapi.com and the youtube-api node. What makes this different from a zap is the middle node — it forms a view about the HubSpot item before anything reaches YouTube.
{
"id": "734bf600-10a2-4f10-ab87-986e90460170",
"name": "HubSpot → YouTube",
"nodes": [
{
"id": "391c606f-ae9d-480d-ac79-4b44e1fec7a2",
"text": "Poll HubSpot",
"x": 512,
"y": 144,
"isEditing": false,
"type": "trigger-timer",
"icon": "connect",
"category": "trigger",
"isSelected": false,
"parameters": {
"interval": "15",
"unit": "minutes"
},
"description": "Checks HubSpot on a schedule.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
},
{
"id": "cb215b97-fde3-44f4-a17d-85a701559ee0",
"text": "Read it and decide",
"x": 512,
"y": 336,
"isEditing": false,
"type": "agnt-agent",
"icon": "connect",
"category": "action",
"isSelected": false,
"parameters": {
"instructions": "Read the HubSpot item. Decide whether it warrants action in YouTube, and explain why."
},
"description": "Decides whether this HubSpot item warrants anything in YouTube.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
},
{
"id": "58bb38d5-675b-419d-ab96-d7940054d672",
"text": "Act in YouTube",
"x": 512,
"y": 528,
"isEditing": false,
"type": "youtube-api",
"icon": "connect",
"category": "action",
"isSelected": false,
"parameters": {
"action": "ADD_VIDEO_TO_PLAYLIST"
},
"description": "Interact with the YouTube API to manage videos, comments, playlists, and more.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
}
],
"edges": [
{
"id": "535c7a8c-c6ee-42e4-a946-6efef47678f4",
"start": {
"id": "391c606f-ae9d-480d-ac79-4b44e1fec7a2",
"type": "output"
},
"end": {
"id": "cb215b97-fde3-44f4-a17d-85a701559ee0",
"type": "input"
},
"startX": 800,
"startY": 168,
"endX": 512,
"endY": 360
},
{
"id": "c79431f6-1957-485a-abcc-2706e7af1e0c",
"start": {
"id": "cb215b97-fde3-44f4-a17d-85a701559ee0",
"type": "output"
},
"end": {
"id": "58bb38d5-675b-419d-ab96-d7940054d672",
"type": "input"
},
"startX": 800,
"startY": 360,
"endX": 512,
"endY": 552
}
],
"zoomLevel": 1,
"canvasOffsetX": 0,
"canvasOffsetY": 0,
"isTinyNodeMode": false
}Install Lead Researcher
Lead Researcher is a working agent built around HubSpot. Install it, point its last step at YouTube, and you have this hand-off without building it from an empty canvas.
Runs on your own machine · See what it does
Build it in AGNT
- Get AGNT Community Core. Free, local, no sign-up needed to run a workflow.
- Add both connections to the vault — HubSpot takes one OAuth sign-in, YouTube takes one OAuth sign-in.
- Build the three nodes above, or start from a marketplace workflow and edit it. The agent in the middle is the part worth spending time on.
- Run it once with an approval gate in place. The receipt tells you what it read, what it concluded, and what it changed in YouTube.
HubSpot and YouTube — common questions
Can I connect HubSpot to YouTube without writing code?
You can build it entirely from the canvas. Authorise HubSpot with one OAuth sign-in, YouTube with one OAuth sign-in, then tell the agent what every inbound lead researched and scored should look like once YouTube is involved. Code is an option for the unusual cases, never a requirement for the common ones.
How is this different from a field-mapping HubSpot to YouTube automation?
The difference shows up on the messy inputs. A rule chain needs every case enumerated in advance; an agent handles every inbound lead researched and scored the way a colleague would — reading the HubSpot context, judging it, then writing to YouTube with the reasoning recorded.
Does my HubSpot and YouTube data leave my machine?
Not to us. AGNT runs locally and both sets of credentials are encrypted on your own disk. Outbound traffic goes only to HubSpot, YouTube and whichever model you chose — and pointing that at Ollama or LM Studio keeps everything on your hardware.
What does a HubSpot and YouTube run leave behind?
A receipt: what was read in HubSpot, which tools ran with which arguments, what the agent concluded, and what it wrote to YouTube. Anything consequential can sit behind an approval gate so a person signs off before it happens.
