Project mgmt × Social
AsanaYouTubeAGNT

Automate Asana + YouTube

Team tasks, due dates and the follow-through between them. 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.

Install Meeting Follow-Through → Get AGNT free

Meeting Follow-Through is a ready-made agent built around Asana; point its last step at YouTube to finish this hand-off.

Automations teams run

These are not field mappings. An agent reads the Asana side, works out what it means, and only then decides what — if anything — should happen in YouTube.

When a task is created or completed in Asana…

…an agent can pull transcripts and stats in YouTube — after reading the context and deciding it should.

When a due date nears in Asana…

…an agent can draft descriptions and chapters in YouTube — after reading the context and deciding it should.

When a project updates in Asana…

…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 tasks with owners in Asana — with the reasoning recorded in the run’s receipt.

When a comment arrives in YouTube…

…an agent can update status and comments in Asana — with the reasoning recorded in the run’s receipt.

Copy this Asana → YouTube workflow

Concretely: a custom-api call to app.asana.com on one side, the youtube-api node on the other, and an agent in between that can decline. Deciding not to write into YouTube is a recorded outcome, not a silent one.

Asana to YouTube: poll asana → read it and decide → act in youtube TRIGGER trigger-timer Poll Asana Every fifteen minutes. ACTION agnt-agent Read it and decide Judged against your own rules. ACTION youtube-api Act in YouTube Runs ADD_VIDEO_TO_PLAYLIST.
Neither Asana nor YouTube credentials leave your machine — both live in a local vault.
Asana → YouTubepaste into a new workflow
{
  "id": "2d32574e-04e2-4d25-a60b-c23bd1734cda",
  "name": "Asana → YouTube",
  "nodes": [
    {
      "id": "ab81019e-7ebb-4c2e-a17f-7d0c2e29ca10",
      "text": "Poll Asana",
      "x": 512,
      "y": 144,
      "isEditing": false,
      "type": "trigger-timer",
      "icon": "connect",
      "category": "trigger",
      "isSelected": false,
      "parameters": {
        "interval": "15",
        "unit": "minutes"
      },
      "description": "Checks Asana on a schedule.",
      "error": null,
      "isActive": false,
      "output": null,
      "outputs": {}
    },
    {
      "id": "1b32119c-8ac0-410a-a504-eb641cf86178",
      "text": "Read it and decide",
      "x": 512,
      "y": 336,
      "isEditing": false,
      "type": "agnt-agent",
      "icon": "connect",
      "category": "action",
      "isSelected": false,
      "parameters": {
        "instructions": "Read the Asana item. Decide whether it warrants action in YouTube, and explain why."
      },
      "description": "Decides whether this Asana item warrants anything in YouTube.",
      "error": null,
      "isActive": false,
      "output": null,
      "outputs": {}
    },
    {
      "id": "c377b5e5-35ff-495e-a5af-8539272399a8",
      "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": "089a28dd-da14-41b3-a7f1-07f4f9914a1e",
      "start": {
        "id": "ab81019e-7ebb-4c2e-a17f-7d0c2e29ca10",
        "type": "output"
      },
      "end": {
        "id": "1b32119c-8ac0-410a-a504-eb641cf86178",
        "type": "input"
      },
      "startX": 800,
      "startY": 168,
      "endX": 512,
      "endY": 360
    },
    {
      "id": "90eedf32-df1a-489e-ac34-276481804220",
      "start": {
        "id": "1b32119c-8ac0-410a-a504-eb641cf86178",
        "type": "output"
      },
      "end": {
        "id": "c377b5e5-35ff-495e-a5af-8539272399a8",
        "type": "input"
      },
      "startX": 800,
      "startY": 360,
      "endX": 512,
      "endY": 552
    }
  ],
  "zoomLevel": 1,
  "canvasOffsetX": 0,
  "canvasOffsetY": 0,
  "isTinyNodeMode": false
}

Install Meeting Follow-Through

Meeting Follow-Through is a working agent built around Asana. 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

What building this looks like

  1. Install AGNT — it runs on your own machine and needs no account to start.
  2. Authorise YouTube (one OAuth sign-in) and Asana (one OAuth sign-in). Nothing is stored anywhere but your disk.
  3. Describe the job in plain language, or paste the definition above; custom-api does the reading and youtube-api the writing.
  4. Gate anything you would not want done unattended, then let it run and read the first receipt end to end.

Asana and YouTube — common questions

Can I connect Asana to YouTube without writing code?

You can build it entirely from the canvas. Authorise Asana with one OAuth sign-in, YouTube with one OAuth sign-in, then tell the agent what meeting decisions become assigned tasks 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 Asana to YouTube automation?

The difference shows up on the messy inputs. A rule chain needs every case enumerated in advance; an agent handles meeting decisions become assigned tasks the way a colleague would — reading the Asana context, judging it, then writing to YouTube with the reasoning recorded.

Does my Asana and YouTube data leave my machine?

AGNT Community Core is local-first, so there is no vendor middleman holding your Asana or YouTube tokens. The runtime talks directly to both services. Choose a local model and the content of what it reads never leaves the machine at all.

What does a Asana and YouTube run leave behind?

Every run is recorded end to end — the Asana items examined, the decision and its reasoning, the resulting YouTube write. That record is what makes it reasonable to let this run unattended, and what lets you widen its remit on evidence.

Give AI a job. Get the proof.