AITable API
Agent-ready OpenAPI document · curated by JenticProductivityCollaborationbearer14 EndpointsREST
Know of an official OpenAPI document? Contribute it →
For Agents
Read and write rows in collaborative datasheets, manage fields and views, and upload attachments. Designed for agents that operate spreadsheets as a backend.
Use for: List all spaces I can access, Get records from datasheet {id} where Status equals Open, Create a new record in datasheet {id} with the given fields, Update the Status field on records 1, 2, and 3
Not supported: Does not handle billing, document editing, or chat - use for collaborative datasheet records, fields, and attachments only.
Jentic publishes the only available OpenAPI specification for AITable API, keeping it validated and agent-ready. AITable is a collaborative data platform - a programmable spreadsheet-database hybrid in the same family as Airtable. The 14-endpoint Fusion API exposes spaces and nodes (workspaces and tabs), datasheet records, fields, views, attachment uploads, and contact directories. Authentication is bearer-token based, and operations are designed for batch record creation, updating, and deletion.
Install Jentic One Beta
Connect the AITable API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the AITable API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Faitable.ai%2Faitable" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Faitable.ai%2Faitable" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with AITable API.
List spaces and traverse the node tree to find a target datasheet
Read records from a datasheet with filtering and pagination
Create, update, and delete records in batches
Add and remove fields on a datasheet to evolve its schema
List views configured on a datasheet for filtered reads
Upload file attachments and attach them to records
Look up space members and roles for permission decisions
Use Cases
Patterns agents use AITable API for, with concrete tasks.
★ Spreadsheet as agent memory
Use an AITable datasheet as a structured persistent store for an AI agent - write task results into rows, query past results by status, and update fields as work progresses. Batch endpoints let the agent process many rows in one call.
POST to /datasheets/{datasheetId}/records with an array of new task rows, then PATCH the same endpoint to mark them as 'In Progress'
Internal tool back-end
Power a lightweight internal tool (CRM, ticket tracker, asset register) by writing to AITable records. The Fields endpoints let an admin agent evolve schemas, and Views give read-only filtered cuts to share with stakeholders.
Create a 'Status' field on the datasheet via POST /datasheets/{id}/fields, then bulk-update existing records to set the new field
Attachment ingestion
Allow an agent to capture screenshots, PDFs, or audio files and attach them to records. POST /datasheets/{id}/attachments uploads the file, and the resulting attachment id can be referenced by an attachment field on a record.
Upload report.pdf via POST /datasheets/{id}/attachments and PATCH the matching record's Attachments field with the returned id
AI agent integration via Jentic
An agent uses Jentic to discover AITable's record operations by intent, loads the schema, and runs reads/writes. The bearer token is held in your Jentic One instance, so agents can update spreadsheets without ever touching the credential.
Search Jentic for 'create rows in a datasheet', load the AITable POST /datasheets/{datasheetId}/records operation, and execute with the target datasheet id
Key Endpoints
14 endpoints — jentic publishes the only available openapi specification for aitable api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
GET
/spaces
List spaces
GET
/datasheets/{datasheetId}/records
Get records with filter and pagination
POST
/datasheets/{datasheetId}/records
Create records in batch
PATCH
/datasheets/{datasheetId}/records
Update records in batch
DELETE
/datasheets/{datasheetId}/records
Delete records in batch
POST
/datasheets/{datasheetId}/fields
Create a field
POST
/datasheets/{datasheetId}/attachments
Upload an attachment
GET
/spaces
List spaces
GET
/datasheets/{datasheetId}/records
Get records with filter and pagination
POST
/datasheets/{datasheetId}/records
Create records in batch
PATCH
/datasheets/{datasheetId}/records
Update records in batch
DELETE
/datasheets/{datasheetId}/records
Delete records in batch
POST
/datasheets/{datasheetId}/fields
Create a field
POST
/datasheets/{datasheetId}/attachments
Upload an attachment
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring AITable by hand means handling its bearer token, threading datasheet ids through record and field paths, and writing your own retry logic. Through Jentic you install once, import AITable from the API Directory, store the token once, and your agent calls it.
Permission scoping
AITable puts the datasheet id in the URL path (/datasheets/{datasheetId}/records), so a rule can pin your agent to one datasheet. You choose the operations it may call, so record deletion is only included if you add it.
Credential isolation
Your AITable bearer token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'create rows in a spreadsheet', and Jentic returns the matching AITable record operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using AITable API through Jentic.
Why is there no official OpenAPI spec for AITable API?
AITable does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call AITable API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.
What authentication does the AITable API use?
AITable uses HTTP bearer authentication - supply your token in the Authorization: Bearer <token> header. Through Jentic, the token is stored encrypted in your Jentic One instance and injected at execution, so the agent never sees it.
Can I create multiple records in one call?
Yes. POST /datasheets/{datasheetId}/records accepts an array of records, and PATCH and DELETE on the same path also operate in batch. This is the recommended way to keep request volume low.
How do I read records from a specific view through Jentic?
Use the Jentic search query 'get records from a datasheet view'. Jentic returns the GET /datasheets/{datasheetId}/records operation; pass the viewId query parameter to scope the read to that view.
Are there rate limits on the AITable Fusion API?
AITable applies plan-based rate limits that are not enumerated in the OpenAPI spec. Implement retry-with-backoff on 429 responses and prefer batch endpoints to stay under quotas.
Can I limit what my agent is allowed to do with the AITable API?
Yes. Because you run Jentic One yourself, your own rules decide which AITable operations and credentials the agent can use. AITable puts the datasheet id in the URL path, such as /datasheets/{datasheetId}/records, so a rule can pin the agent to a single datasheet. You also choose exactly which operations it may call, so destructive actions like DELETE on records are only available if you add them.
GET STARTED