Airtable
Also known as: Airtable Omni, Omni, Field Agents, Airtable AI
Relational app platform and agent builder where Omni configures agents from plain language and Field Agents run autonomously inside every record, with enterprise governance, audit logs and model choice.
Airtable is a relational database and app building platform that has repositioned around agents. Its agent surface has two named parts. Omni is a conversational builder that takes a plain language description and configures the tables, interfaces and agents to match. Field Agents are agents attached to fields that perform work inside every record of an app at scale. They analyze documents, search the web, generate and edit images, translate content and extract insights from transcripts. Field Agents can be set to run continuously whenever data is added or updated rather than being manually invoked.
For governance, Airtable ships enterprise audit logs through both an admin panel and a dedicated Audit Logs API with published event types, role based access control, SSO with SAML, MFA, SCIM provisioning, enterprise key management and an admin panel report for AI credit consumption. Enterprise customers choose which models are enabled across OpenAI, Anthropic and Meta, with an Amazon Bedrock option under which model providers never handle customer data. Model providers do not retain customer data, and customer data is not used for model training.
Airtable is cloud only, with EU data residency and tenant level key management available but no self hosted, VPC or on premises option, and it is not FedRAMP authorized. HIPAA support requires an Enterprise Scale plan, a signed health information exhibit and specific configuration. Admins control where AI is enabled and what data agents can reach. There is no approval step before an individual agent action runs.
Vendor details
Canonical URL
https://www.airtable.com
Category
Agent builder
Subcategory
No code agent building on a relational data platform
Funding status
Acquired, pending close. On 30 July 2026 Bending Spoons entered a definitive agreement to acquire Airtable for an enterprise value of $1.285 billion, roughly $2.25 billion equity value, all cash. Both companies continue to operate independently until closing, which is subject to regulatory approval. It is Bending Spoons' first acquisition since its Nasdaq listing on 1 July 2026, following AOL in January and Eventbrite in March. The agent business was carved out before signing. Per Bending Spoons' SEC Form 6-K, assets and liabilities relating to the Hyperagent business line were transferred by Airtable to a separate entity, Hyperagent Inc., which is a named party to the purchase agreement, with the founders' holding company retaining ownership. The acquisition therefore covers the core database and workflow platform, approximately 500,000 organizations, 80% of the Fortune 100 and about $480m ARR as of June 2026, and excludes the standalone agent orchestration platform. Earlier history: founded 2013 by Howie Liu, Andrew Ofstad and Emmett Nicholas; peak valuation $11.7bn in 2021 falling to roughly $4bn on secondary markets before the sale; cumulative raise around $1.3-1.4bn; layoffs of 254 in December 2022 and 237 in September 2023. Acquired the AI research startup DeepSky, formerly Gradient, in October 2025 and appointed David Azose, previously head of engineering for ChatGPT business products at OpenAI, as chief technology officer; Azose left in July 2026.
Company status
acquired
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Airtable has native integrations with Slack, Google Drive, Salesforce, Jira and Zendesk, plus a public marketplace. Developers get the Web API, Enterprise API, Audit Logs API and Shares API, a developer portal, personal access tokens, webhooks, scripting and custom extensions. An official MCP server and skills give external AI agents access to bases, records and workflows, and a Claude integration with its own landing page brings Airtable data into Claude.
In practice
A marketing team points Field Agents at a table of campaign briefs so that every new row is automatically turned into on brand concepts and localized copy variants without anyone opening the record.
An operations team drops thousands of contracts into a base and agents extract structured terms into fields, converting static documents into live operational data other teams can query.
A revenue team runs web search agents continuously against an account table so competitor and news intel refreshes itself in the background rather than in a weekly manual sweep.
Sources & related URLs
Related / legacy domains
Research sources
Agentic Index coverage score
11.0 / 14 capabilities · 79%
| Integrations & Tool Calling | Full |
|---|---|
|
Airtable has native integrations for Slack, Google Drive, Salesforce, Jira and Zendesk, with a full integrations directory and a public marketplace. Agents call document analysis, web search and image generation tools. Sourceairtable.com/integrationsread 2026-09-01 |
|
| Workflow Orchestration | Full |
|
Omni is a conversational builder that sets up the work from a plain language request. It creates tables and fields, including field agents, builds interface pages and AI-generated interface elements, and creates or updates automations. A single agentic framework sits behind both Omni and Field Agents, and its agents reason, plan and orchestrate actions across the entire operation to accomplish complex tasks with minimal input. Underneath sits a dedicated automations engine as a core platform module. Sourceairtable.com/platform/ai-agents, support.airtable.com using-omni-ai-in-airtable and the Airtable engineering blogread 2026-09-01 |
|
| Knowledge Grounding & RAG | Full |
|
Agents are grounded in the customer's relational base and can read across connected data. Document analysis agents turn contracts, invoices and reports into structured fields, and web search agents pull real time external data into the same records. Sourceairtable.com/platform/ai-agentsread 2026-09-01 |
|
| Human Oversight & Guardrails | Partial |
|
Admins enable AI per workspace, customers control what data agents can access, role based access control applies and all agent activity is auditable. There is no approval gate or review step before an individual agent action runs. Sourceairtable.com/platform/ai-agentsread 2026-09-01 |
|
| Security, Identity & Governance | Full |
|
Airtable holds SOC 2 Type 2, with the report available on request, ISO/IEC 27001:2022 and ISO/IEC 27701:2019 with published certificates, TX-RAMP Level 2 with a certificate, and HIPAA. It also runs GDPR, UK GDPR and CCPA/CPRA programs, offers a signable DPA and keeps a subprocessor list. Controls include SAML single sign on and extra admin features on Enterprise, two-factor authentication, customizable collaborator permissions, view access restricted by password or email domain, SCIM provisioning and enterprise key management that lets customers hold their own keys at rest. Airtable also runs a HackerOne bug bounty program and publishes security and privacy whitepapers, and completed CAIQ, SIG Lite and HECVAT questionnaires are available under NDA. Sourceairtable.com/company/trust-and-securityread 2026-09-01 |
|
| Observability & Auditability | Full |
|
Enterprise audit logs are available through the admin panel and through a dedicated Audit Logs API with published event types and several years of history. Revision history on each record gives a visual activity feed of every change, and that is where Field Agent output lands, so an agent's writes can be inspected at the row it wrote. Admin reports cover AI credit consumption, API and token owners and enterprise key management status, and all Field Agent activity is governed and auditable. Sourceairtable.com developer audit log event types, airtable.com/company/trust-and-security and airtable.com/platform/ai-agentsread 2026-09-01 |
|
| Memory & State Persistence | Partial |
|
Agent outputs persist as structured fields in the relational base and become shared state that other agents read, and HyperDB scales to 100M records. There is no cross session agent memory or learned context layer separate from the data store. Sourceairtable.com/platform/hyperdbread 2026-09-01 |
|
| Deployment & Data Residency | Partial |
|
Customers can have their data stored in the European Union, and Enterprise customers get enterprise key management, so data at rest is held under customer-owned keys. Models can also be served through Amazon Bedrock so providers never touch customer data. There is no self-hosted, on-premises, VPC or customer-cloud deployment and no FedRAMP authorization, so the platform is cloud only, with a residency option. Sourceairtable.com/company/trust-and-security and airtable.com/company/data-residency-faqsread 2026-09-01 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
Customers can adopt packaged assets in three forms without building anything. AI Plays is a browsable library of premade AI workflows at airtable.com/ai-plays, each with its own page, including campaign concept ideation, brand and compliance review, localization of image and copy variants, and contract operations. Four ready agent types are offered, document analysis, web search, image generation and custom. A catalog of pre-set field agents lets a user pick a suggested agent, which opens Omni with a request to build it, so the agent is adopted in one step and stays editable. An extensive template gallery and a public marketplace sit alongside. Sourceairtable.com/ai-plays, airtable.com/platform/ai-agents and support.airtable.com using-airtable-ai-in-fieldsread 2026-09-01 |
|
| Triggers & Channel Coverage | Full |
|
Field Agents can run automatically whenever data is added or updated, so they work continuously without anyone starting them. Automations provide event triggers, and work also starts from the web, desktop and mobile apps and through webhooks. Sourceairtable.com/platform/ai-agentsread 2026-09-01 |
|
| Model Flexibility & Routing | Full |
|
Enterprise customers decide which models are enabled and choose among OpenAI, Anthropic and Meta models. Anthropic Claude models are served through Amazon Bedrock so providers never handle customer data, and providers neither retain data nor train on it. Sourceairtable.com/platform/ai-agentsread 2026-09-01 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
Developers get the Web API, Enterprise API, Audit Logs API and Shares API with a developer portal, personal access tokens, webhooks, scripting and custom extensions. An official MCP server and skills expose bases, records and workflows to external agents, and a Claude integration is promoted on its own landing page. Sourceairtable.com/developers/web/api/introductionread 2026-09-01 |
|
| Testing, Debugging & Optimization | Partial |
|
Omni produces a working configuration that the user reviews and then refines in conversation, and its limits are spelled out, including which interface layouts it cannot create. Automations keep run history for debugging a failed step. There is no agent evaluation harness, scored or repeatable test run, regression suite or output scoring. Sourcesupport.airtable.com using-omni-ai-in-airtable and airtable.com/platform/automationsread 2026-09-01 |
|
| Browser & Computer Use | Not documented |
|
Web search agents bring real time web data into records, but browser control, page navigation and computer use are not described anywhere in the product. Sourceairtable.com/platform/ai-agentsread 2026-09-01 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Airtable's audit log now shows whether a person or an agent took each action, and in which base. Actions by Omni, Airtable's own assistant, are attributed directly, while actions from outside AI tools trace back to the integration and the person who connected it. Events inside a base, such as creating a table, updating an interface page or deleting a comment, are rolling out now, and the log can be filtered, exported, or streamed through the audit API into security tools.
Bears on: Security / enterprise
View sourceOmni, Airtable's built in AI assistant, now plans and carries out larger jobs from start to finish instead of handling one request at a time. It can turn up to 10 uploaded files into tables and fields, write the code for a custom interface page, and build or diagnose an automation end to end. It is live for workspaces in AI Labs, which an admin can turn on except on HIPAA accounts, and reaches others over the following weeks.
Bears on: Human approval / guardrails
View sourceAgents connected to Airtable's MCP server can now create and edit the custom scripts inside automations. Until now the MCP automation tools could not touch automations with Script actions, so those code steps had to be written and fixed by hand in the Airtable interface.
Bears on: Workflow orchestration
View sourcePricing
$20 per user per month on Team, billed annually.
Seats, counting users with edit permissions, plus AI credits for agent runs.
Included quota
Seat price covers platform use. AI credits are allocated by plan, and each Field Agent run consumes credits. Business plan admins see credit usage in workspace settings, and Enterprise Scale admins see it in the admin panel Reports page.
What is public
List prices are published for Free, Team at $20 and Business at $45 per user per month billed annually. Enterprise Scale is custom and sold through sales.
Billing mechanics
Charged per seat, counting only users with edit permissions on at least one base in the workspace. Read only collaborators, form submissions and share links are free. Charges are prorated for users added mid cycle. Team and self serve Business are card billed. Business and Enterprise Scale bought through sales can be invoiced annually via PO, ACH, wire or check.
Cost watchouts
Agent costs are decoupled from seat count. A small team running agents across a large base can consume credits far faster than its seat spend implies. HIPAA workloads require Enterprise Scale plus a signed health information exhibit, so regulated use needs the custom priced tier regardless of team size. EU data residency and enterprise key management are enterprise features.
Variable cost rationale
Seats are billed per user with edit permissions at a published list price, so the seat line moves only with the number of editors. AI credits are the metered part, and every Field Agent run consumes them. Field Agents are designed to run continuously across every record, so credit use grows with data volume rather than headcount. Each plan carries a monthly credit allocation, pooled across the workspace and reset each month without rollover. When it runs out, self serve plans buy extra credit packs, and sales led customers add credits through their account team. No credit cost is published for a Field Agent run.
Additional watchouts
The headline seat price does not include agent execution. AI credits are a separate cost line, and an agent heavy deployment that uses up the monthly allocation needs extra credit packs.
Overage / add-ons
Record and attachment overages block further additions until upgrade but data is never removed. Automation and API usage is capped at the plan limit rather than billed as overage.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free plan available for individuals and very small teams
Lowest paid plan
Team at $20 per user per month, billed annually
Commercial notes
Enterprise Scale adds unlimited org units, workspaces and bases. Special plans exist for nonprofits and education. Customers on the legacy Enterprise plan keep their features until renewal.
Key ambiguities
Each plan carries a monthly AI credit allocation per editor or paid user, 500 on Free, 15,000 on Team, 20,000 on Business and 25,000 on Enterprise Scale, pooled across the workspace and expiring at month end. The credit cost of a Field Agent run is not published, so the usage half of the bill cannot be modeled in advance.
Cancellation / refund
Charges are prorated for editors added mid cycle, and Business and Enterprise Scale bought through sales can be invoiced annually. No cancellation or refund terms are published.
Missing data
The credit cost of a Field Agent run.
Related vendors
- Lindy — Lindy is an AI teammate that lives in Slack, answers from your tools…
- Activepieces — Open source, MIT licensed automation platform where every one of 700…
- Agenta — Agenta is an open source workspace where teams build AI agents by…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No code platform for building and running AI agents, with a…
- Aigensei — Enterprise agentic workflow platform that runs business processes…
Alternatives to Airtable
The closest documented capability profiles to Airtable among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Make11.0 / 14Matches Airtable across all 14 documented capabilities
- Dify12.0 / 14Fuller documented coverage on Human Oversight & Guardrails and Deployment & Data Residency
- DronaHQ11.0 / 14Fuller documented coverage on Testing, Debugging & Optimization
- LuMay12.0 / 14Fuller documented coverage on Human Oversight & Guardrails and Deployment & Data Residency
- Moveo.AI12.0 / 14Fuller documented coverage on Deployment & Data Residency and Testing, Debugging & Optimization
- Pickaxe10.0 / 14A lighter documented profile than Airtable
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded