Data · Integration

AI agents for Airtable

Structured records with an API worth automating. AGNT connects to Airtable so agents can read what happens there, reason about it, and act — with a receipt for every run.

Install Document Extractor → Get AGNT free

Document Extractor is a ready-made agent that works in Airtable — free, and it runs on your machine.

Airtable and AGNT, in brief

What it does	Lets an AGNT agent read from and act in Airtable.
Connects with	Bearer — held in the local vault
AGNT node	custom-api, or the zapier-action bridge
Runs when	A record is created
Typical build time	Ten minutes
Where data goes	Nowhere by default — AGNT runs on your machine and credentials never leave it.

What you can automate

Reacts when…

a record is created
a field changes
a view gains a row

Agents can…

create and update records
query views for reporting
link records across tables

Teams use it for

pipeline trackers that stay current
content calendars agents maintain
ops databases fed from email and forms

Build it: the Airtable workflow

Design goal for Airtable: pipeline trackers that stay current; content calendars agents maintain; ops databases fed from email and forms. The template below supplies configurable nodes, not the complete logic for those goals.

Use this Airtable setup template to arrange the schedule, input review and API operation. Configure the account-specific fields and add your own decision and approval controls before activation.

Configuration example for Airtable. API and model calls may send data to your selected providers.

Airtable — read, decide, actSetup template · configure before activation

This is a schema-checked starting point, not an end-to-end tested automation. Replace every CONFIGURE_ value, choose the operations you intend, connect credentials and map source outputs into later inputs. An edge orders steps; it does not supply a condition, an approval gate or a field mapping. Add and test those controls explicitly before any write. Cloud APIs and model providers may receive data. Keep the workflow inactive until tested with fixtures.

{
  "id": "0f713431-8871-4194-a9f1-7a11aa1f3f58",
  "name": "Airtable — read, decide, act",
  "nodes": [
    {
      "id": "24c22b80-c572-4da5-a9eb-aa2dc2fba486",
      "text": "Run on a schedule",
      "x": 512,
      "y": 144,
      "isEditing": false,
      "type": "trigger-timer",
      "icon": "clock",
      "category": "trigger",
      "isSelected": false,
      "parameters": {
        "fireOnStart": "No",
        "scheduleType": "Interval",
        "schedule": "Every 15 Minutes"
      },
      "description": "Setup template for Timer Trigger. This trigger node fires the workflow at specified intervals or at a specific time. Configure credentials, inputs and output mapping before use.",
      "error": null,
      "isActive": false,
      "output": null,
      "outputs": {}
    },
    {
      "id": "b7b5762e-8af2-4a24-a5cb-ac7a56c624f4",
      "text": "Review source and draft",
      "x": 512,
      "y": 336,
      "isEditing": false,
      "type": "agnt-agent",
      "icon": "agnt",
      "category": "action",
      "isSelected": false,
      "parameters": {
        "agentId": "CONFIGURE_AGENTID",
        "message": "Decide what needs to happen in Airtable. Explain your reasoning.\nSource input: CONFIGURE_SOURCE_INPUT. Produce a reviewable draft only; do not take external actions."
      },
      "description": "Setup template for Agent Chat. Chat with an AI agent from your agent library. Select an agent and send messages to interact with it within your workflow. Configure credentials, inputs and output mapping before use.",
      "error": null,
      "isActive": false,
      "output": null,
      "outputs": {}
    },
    {
      "id": "f9241d2c-5856-4287-a229-d02331b3a1ca",
      "text": "Call the Airtable API",
      "x": 512,
      "y": 528,
      "isEditing": false,
      "type": "custom-api",
      "icon": "connect",
      "category": "action",
      "isSelected": false,
      "parameters": {
        "url": "https://api.airtable.com/v0/{baseId}/{tableName}",
        "method": "GET",
        "authType": "None",
        "headers": "{}",
        "query": ""
      },
      "description": "Setup template for Custom API Request. This action node makes a custom API request to any endpoint with configurable method, headers, and authentication. Configure credentials, inputs and output mapping before use.",
      "error": null,
      "isActive": false,
      "output": null,
      "outputs": {}
    }
  ],
  "edges": [
    {
      "id": "01ceb820-36ea-43d4-abd0-6c344a786d20",
      "start": {
        "id": "24c22b80-c572-4da5-a9eb-aa2dc2fba486",
        "type": "output"
      },
      "end": {
        "id": "b7b5762e-8af2-4a24-a5cb-ac7a56c624f4",
        "type": "input"
      },
      "startX": 800,
      "startY": 168,
      "endX": 512,
      "endY": 360
    },
    {
      "id": "69c1c42d-178e-4d3c-ab75-d4d3e9383f24",
      "start": {
        "id": "b7b5762e-8af2-4a24-a5cb-ac7a56c624f4",
        "type": "output"
      },
      "end": {
        "id": "f9241d2c-5856-4287-a229-d02331b3a1ca",
        "type": "input"
      },
      "startX": 800,
      "startY": 360,
      "endX": 512,
      "endY": 552
    }
  ],
  "zoomLevel": 1,
  "canvasOffsetX": 0,
  "canvasOffsetY": 0,
  "isTinyNodeMode": false
}

Configure Custom API Request

This action node makes a custom API request to any endpoint with configurable method, headers, and authentication.

url — The URL of the API endpoint Current example: https://api.airtable.com/v0/{baseId}/{tableName}.
method — The HTTP method for the request Current example: GET.
authType — The type of authentication Current example: None.
query — Query parameters for the request (e.g., 'key1=value1&key2=value2') Current example: .
headers — Optional headers for the request. e.g., {"Content-Type": "application/json"} Current example: {}.

Install Document Extractor — it runs on Airtable

Document Extractor is a working agent that uses Airtable. Installing it drops the whole workflow onto your canvas — connected, editable, and yours to change.

Install Document Extractor → Don’t have AGNT? Get it free

Runs on your own machine · See what it does

Structure without a database project

Airtable occupies the useful middle ground between a spreadsheet and a real database: typed fields, linked records and views, with an API worth automating against. For agent output that needs structure but not a schema migration, it is often the right destination.

Trackers that maintain themselves

Pipeline trackers, content calendars and ops databases share one failure mode — they go stale because updating them is somebody’s afternoon. An agent writing records from the events that should have updated them removes that entirely.

Connecting Airtable today

There is no first-party Airtable node yet, and a page implying otherwise would cost you an afternoon. What works today is the generic custom-api node pointed at Airtable’s own API, authenticating with bearer.

What you need	Value
Endpoint	`https://api.airtable.com/v0/{baseId}/{tableName}`
Method	`POST`
Authentication	Bearer
Header	`Authorization: Bearer {personalAccessToken}`
Reference	Airtable API documentation

Worth knowing: Records are wrapped in a `records` array even when you are creating exactly one.

The part that catches people out

Records are wrapped in a `records` array even when you are creating exactly one.

Everything else about Airtable behaves the way you would expect, so once that is handled the rest of the build is ordinary. The POST above is the shape every other call takes.

Connect Airtable in two minutes

Download AGNT Community Core — free, local-first, no account needed to run.
Connect by pasting an API key into AGNT’s vault — stored encrypted on your machine, never uploaded.
Drop the Airtable node into a workflow or hand it to an agent — the first run produces a receipt you can read line by line.