AI agents for Google Drive
Where the documents live — and pile up. AGNT connects to Google Drive so agents can read what happens there, reason about it, and act — with a receipt for every run.
Document Extractor is a ready-made agent that works in Google Drive — free, and it runs on your machine.
Google Drive and AGNT, in brief
| What it does | Lets an AGNT agent read from and act in Google Drive. |
|---|---|
| Connects with | One OAuth sign-in |
| AGNT node | google-drive-api |
| Runs when | A file lands in a folder |
| Typical build time | Two minutes |
| Where data goes | Nowhere by default — AGNT runs on your machine and credentials never leave it. |
What you can automate
Reacts when…
- a file lands in a folder
- a doc is updated
- a file is shared
Agents can…
- read and summarise documents
- file outputs into folders
- export and convert formats
Teams use it for
- auto-summarise incoming docs
- keep a folder of reports the agents maintain
- extract data from uploads
Copy this Google Drive workflow
A concrete shape to start from: the workflow wakes when a file lands in a folder in Google Drive. The agent gathers the surrounding context, forms a view, and where it is warranted goes on to read and summarise documents — or to file outputs into folders. Nothing is copied blindly, and choosing to take no action is a legitimate outcome recorded in the receipt.
Three nodes carry that: something happens in Google Drive, an agent reads it and forms a view, and it acts only where that view says it should. The definition below is the whole thing — paste it into a new workflow and it loads exactly as drawn.
{
"id": "4540c98c-f0ec-46cb-ac85-6e43b3615b8a",
"name": "Google Drive — read, decide, act",
"nodes": [
{
"id": "4be19b6d-0815-4c9e-ad01-196d0091b0b0",
"text": "Run on a schedule",
"x": 512,
"y": 144,
"isEditing": false,
"type": "trigger-timer",
"icon": "clock",
"category": "trigger",
"isSelected": false,
"parameters": {
"interval": "15",
"unit": "minutes"
},
"description": "Checks Google Drive every fifteen minutes.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
},
{
"id": "b896d70b-1014-41ed-af4b-067c6bcdac5a",
"text": "Read it and decide",
"x": 512,
"y": 336,
"isEditing": false,
"type": "agnt-agent",
"icon": "agnt",
"category": "action",
"isSelected": false,
"parameters": {
"instructions": "Read the Google Drive item and decide whether it warrants action. Explain your reasoning."
},
"description": "Judges the Google Drive item against criteria you wrote in plain language.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
},
{
"id": "634ad971-6f4d-49ae-a72a-5b134585290c",
"text": "Act in Google Drive",
"x": 512,
"y": 528,
"isEditing": false,
"type": "google-drive-api",
"icon": "connect",
"category": "action",
"isSelected": false,
"parameters": {
"action": "LIST_FILES"
},
"description": "Runs LIST_FILES on your behalf.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
}
],
"edges": [
{
"id": "2a6212af-bb12-4ba3-a971-8dbec665327e",
"start": {
"id": "4be19b6d-0815-4c9e-ad01-196d0091b0b0",
"type": "output"
},
"end": {
"id": "b896d70b-1014-41ed-af4b-067c6bcdac5a",
"type": "input"
},
"startX": 800,
"startY": 168,
"endX": 512,
"endY": 360
},
{
"id": "b93bb2c2-c487-4276-ab7f-36aaa6859818",
"start": {
"id": "b896d70b-1014-41ed-af4b-067c6bcdac5a",
"type": "output"
},
"end": {
"id": "634ad971-6f4d-49ae-a72a-5b134585290c",
"type": "input"
},
"startX": 800,
"startY": 360,
"endX": 512,
"endY": 552
}
],
"zoomLevel": 1,
"canvasOffsetX": 0,
"canvasOffsetY": 0,
"isTinyNodeMode": false
}
Install Document Extractor — it runs on Google Drive
Document Extractor is a working agent that uses Google Drive. Installing it drops the whole workflow onto your canvas — connected, editable, and yours to change.
Runs on your own machine · See what it does
Documents arrive faster than anyone reads them
Drive is where files accumulate, and most of them are read once or never. An agent watching a folder can summarise what landed, extract the fields that matter and file the result — turning a folder that grows into a folder that reports.
A working area agents can maintain
Drive is also a good destination. Reports, briefings and extracts written back into a shared folder give non-technical colleagues a familiar place to find agent output, with no new tool to learn and no access request to make.
Inside the Google Drive API node
Interact with Google Drive to perform various operations on files and folders.
What it can do: LIST_FILES UPLOAD_FILE DOWNLOAD_FILE CREATE_FOLDER DELETE_FILE MOVE_FILE GET_FILE_INFO SHARE_FILE
Full Google Drive API parameter reference
| Parameter | Type | What it does |
|---|---|---|
actionrequired |
string | The action to perform on Google Drive LIST_FILES · UPLOAD_FILE · DOWNLOAD_FILE · CREATE_FOLDER · DELETE_FILE · MOVE_FILE · GET_FILE_INFO · SHARE_FILE |
folderId |
string | The ID of the folder (for LIST_FILES, UPLOAD_FILE, CREATE_FOLDER) only when action is LIST_FILES or UPLOAD_FILE or CREATE_FOLDER |
fileName |
string | The name or ID of the file only when action is UPLOAD_FILE or DOWNLOAD_FILE or DELETE_FILE or MOVE_FILE |
fileContent |
string | The content of the file to upload only when action is UPLOAD_FILE |
newFolderName |
string | The name of the new folder to create only when action is CREATE_FOLDER |
destinationFolderId |
string | The ID of the destination folder only when action is MOVE_FILE |
shareEmail |
string | Email address to share the file with only when action is SHARE_FILE |
shareRole |
string | The role to grant to the shared user reader · writer · commenter only when action is SHARE_FILE |
Every parameter above is read from the shipped google-drive-api node, so it cannot drift from the product.
Connect Google Drive in two minutes
- Download AGNT Community Core — free, local-first, no account needed to run.
- Connect with one OAuth sign-in from AGNT’s vault — tokens are stored encrypted on your machine and never leave it.
- Drop the Google Drive node into a workflow or hand it to an agent — the first run produces a receipt you can read line by line.
Google Drive + AGNT — common questions
Can an agent read a document as soon as it lands?
Yes — a file arriving in a folder is a trigger, so processing starts on arrival rather than on a schedule.
What file types can it handle?
Documents, spreadsheets, PDFs and images, including scans handled through vision-capable models.
Can it write results back to Drive?
Yes, filed into the folders you specify and in the formats you choose.