Airtable Release Notes

Introducing Google Drive and OneDrive connectors for Field Agents

NEWS

Today we’re excited to announce the launch of Google Drive + OneDrive connectors in field agents—a powerful new way to connect your files directly to your Airtable workflows. You can now direct field agents to search, reference, and summarize content from your Google Drive and OneDrive documents. Key use cases:

• Get up to speed with context: Instantly search for background information and insights from your Drive or OneDrive to ramp up on new projects—no more digging through folders or old documents.
• Summarize comment threads: Quickly generate overviews of conversations on a document, such as a product requirements doc, so you can drive alignment.
• Search knowledge bases to answer questions: Surface answers from documentation or support articles stored in your cloud drives to resolve questions faster and keep your team moving.
• Refer to specif

• 🥇 We partnered with Rob Weidner (​@Rob_Weidner1) to build the ultimate Fantasy Olympics app on Airtable (in 2 days).
• And you can copy the whole thing and make it your own.
• » Explore it here «

How it works

• 📊 Submit predictions for upcoming events and compete on the live leaderboard
• 📣 Get daily AI-generated digests of results and highlights
• 🔍 Explore historical Olympic data going back decades

And we want you to remix it into something even better.

First, make your picks. Submit your predictions for upcoming events. Track the live leaderboard.

Then, sync the data. Pull these Olympic datasets directly into your own base.

Make a copy, tear it apart. Adapt these techniques to your own apps.

Play along and build something awesome!

Next week, we’ll hear more from Rob about how he built this incredible app in just 2 days.

» Explore it here «

Introducing Superagent

NEWS

We just launched Superagent, and I'm excited to share what we've been building. Hopefully you have seen by now that we just launched Airtable’s first standalone product, Superagent. I am the co-founder and CEO of Superagent, which is an evolution of the acquisition of DeepSky last fall. Most AI agents hit a wall when you ask them to tackle the kind of work that normally takes a team weeks to complete—comprehensive market research, competitive intelligence that tracks evolving landscapes, financial modeling that requires coordinating multiple analytical threads. They either get lost in their own complexity or produce surface-level summaries that miss what actually m

Superagent Launch

We just launched Superagent, and I'm excited to share what we've been building.

Hopefully you have seen by now that we just launched Airtable’s first standalone product, Superagent. I am the co-founder and CEO of Superagent, which is an evolution of the acquisition of DeepSky last fall.

Most AI agents hit a wall when you ask them to tackle the kind of work that normally takes a team weeks to complete—comprehensive market research, competitive intelligence that tracks evolving landscapes, financial modeling that requires coordinating multiple analytical threads. They either get lost in their own complexity or produce surface-level summaries that miss what actually matters.

Superagent is different because it thinks like an organization, not like a single analyst grinding through a checklist. Instead of cramming everything into one context window and hoping for the best, it builds a knowledge graph around business intent. Every piece of research knows why it exists, what goal it serves, and how it connects to other insights. It breaks complex problems into parallel workstreams (like staffing a consulting project), actively seeks out contradictory evidence to avoid echoing consensus, and learns new methodologies on the fly when it encounters unfamiliar domains.

The result? Analyses that used to take weeks now complete in minutes, and the system gets smarter with every problem it solves because it builds institutional knowledge that compounds over time.

We built this because we kept seeing the same problem: businesses have genuinely hard questions that require deep research and synthesis, but the work is too expensive and time-consuming to do at the pace decisions actually need to be made. Superagent changes that equation entirely.

Read more about this from Howie Liu, Airtable CEO here.

Or give it a try yourself at www.superagent.com.

Share what you learn with the community on the Superagent forum board.

Introducing Superagent: The Multi-Agent System That Delivers Finished Work

JAN 27, 2026
5 MIN

WRITTEN BY
Howie Liu
FILED UNDER
Company
SHARE

Ask an agent. Get a team.
When we started Airtable twelve years ago, our bet was simple: software should adapt to how people actually work, not the other way around.
That bet paid off. Today, over 500,000 organizations, including 80% of the Fortune 100, use Airtable to build applications that fit their workflows.
Now we're making the same bet on AI agents. And the breakthrough isn't a smarter single agent; it's multiple agents working together.
Today, we’re announcing Superagent, our first standalone product built on multi-agent coordination. When you ask Superagent a question, you're not getting one AI assistant doing sequential tasks. You're getting a coordinating agent that plans the work, deploys specialists who work in parallel, and synthesizes their output into a finished deliverable you can immediately use.
This approach reflects what I call 'inside out' product thinking: start with what's now technically possible at the frontier of technology, then work backward to create the right product experience. Multi-agent systems represent that frontier today.
Superagent is built on our acquisition of DeepSky and reflects our broader momentum in AI – from hiring David Azose as CTO after he led ChatGPT's business products at OpenAI, to launching Airtable for ChatGPT, to refounding as an AI-native platform. It's live now at superagent.com.

The Breakthrough: Teams of Agents, Not One Agent

Here's what's happening under the hood when you use Superagent:
You ask a question, and Superagent doesn't start searching; instead, it immediately builds a research plan, identifying what needs to be investigated, surfacing dimensions you didn't think to ask about, structuring the work like a team of analysts would.
Then it deploys specialized agents. One investigates financials, another analyzes competitive positioning, another reviews management and recent news. These agents work in parallel, their work coordinated by the system, each contributing their piece to the whole.
Finally, it synthesizes. Superagent takes all the parallel work streams and weaves them into a coherent, polished deliverable – not a wall of text, but a rich, interactive artifact, custom-built for your question.
You're not prompting an AI. You're orchestrating a team. That's the difference between asking a traditional chat product to research a competitor and asking Superagent: instead of a sequential summary built by one agent working through tasks one at a time, Superagent deploys a coordinated team to investigate multiple dimensions simultaneously, then delivers an interactive competitive landscape ready to present.

What This Means for Your Work

The power of multi-agent coordination isn't just about speed. It's about getting outputs you can actually use.
Ask where your US-based premium athleisure brand should expand first in Europe. Superagent doesn't give you a text document. You get an interactive market analysis: demographic breakdowns by country, competitive presence mapped visually, expansion timelines you can filter and explore. It's ready to walk into a meeting and present.
Ask it to evaluate Google as a 3-year investment opportunity. You get a structured assessment detailed with citations to earnings calls and filings, defensibility analysis against OpenAI and Anthropic with side-by-side comparisons, and risk factors that you hadn't considered. It's research that informs your investment thesis immediately, not raw material you need to spend hours processing.
Ask it to brief you on Wells Fargo's AI strategy before pitching them on your compliance product. You get their regulatory posture, recent AI investments with deal details, competitive pressures they're facing, and the specific pain points your product addresses. It's pitch prep that's actually ready to use.
What if every task you tackled came with New York Times-quality data visualization? That would have been unfathomable five years ago. With Superagent's multi-agent architecture, it's the default.
The output isn't raw material. It is the deliverable.
That’s what multi-agent coordination unlocks: agents working in parallel produce deeper intelligence faster, and because the system coordinates their work, identifying dependencies, filling gaps, synthesizing insights, the final output is coherent, polished, and ready to ship. You're not reformatting. You're not synthesizing. You're using it.

How We Built It

• Professional-grade sources. Superagent pulls from premium data sources like FactSet, Crunchbase, SEC filings, and earnings transcripts. Insights are verified, cited, and traceable.
• Open-ended agent harness. Unlike older agents that follow rigid, hard-coded paths, Superagent uses a flexible architecture that gives agents autonomy to navigate different approaches, coordinate with each other, backtrack when needed, and adapt to what each specific task requires.
• Outputs designed for humans. Rich, structured deliverables designed for how people actually think and work. Interactive. Visual. Actionable. Instead of a wall of text, you get a rich, immersive artifact with elements like filterable comparison matrices, expandable detail cards, visual positioning maps.

Why This Matters

We've been talking about agents for two years, but what we had even a year ago weren't real agents. They were workflows: predefined series of steps with some LLM calls mixed in.
Now we have true multi-agent systems that can break complex tasks into components, assign specialists, coordinate their work, and deliver finished output. Multi-agent coordination is the defining architecture of today. We’re moving AI from single-threaded chat to parallel, collaborative intelligence.
This isn't an incremental improvement to software. Agents don't just help you work. They do the work.
Twelve years ago, we bet that software should adapt to work, not the other way around. Today, we're betting that AI agents will become critical infrastructure for every organization. The winners won't be the companies with the fastest models, but the companies that deliver multi-agent systems you can actually trust to complete complex work.
The general-purpose, highly usable multi-agent system is becoming a fundamental primitive for knowledge work. And there's a natural complementarity – almost a yin and yang – between the structured data and application layer that Airtable provides and the autonomous, coordinated intelligence that Superagent delivers.
Over the coming months, we'll be deepening Superagent's integration with Airtable and expanding our premium data sources. You'll soon be able to invoke Superagent directly from your Airtable bases, running research across your pipeline, generating insights that flow back into your structured data, and automating intelligence gathering at scale.

Try It Today

Superagent is live at superagent.com. Ask it to tackle a complex question you're wrestling with (a competitor analysis, a market opportunity, a strategic decision) and see what happens when you stop prompting an AI and start orchestrating a team.
Let's keep building.
—Howie Liu
CEO & Co-founder, Airtable

Hey Airtable Community,

As we step into the month of love and appreciation, there's no better time to celebrate the incredible members who made January such a strong start to 2026 💝

Whether you're planning Valentine's celebrations, gearing up for the big game, or simply enjoying the fresh energy of a new year, we hope you'll take a moment to recognize these outstanding contributors who kicked off 2026 with dedication and helpfulness!

Reminder: When recognizing our Top Contributors, we look at the quantitative data (e.g. likes received, answers given), as well as the quality, to make sure everyone follows our Community Code of Conduct and Guidelines in their activity.

In January, our Top Contributors provided 16 answers, 337 replies, and received 173 likes. And, at the top of the leaderboard, our top 5 earners cumulatively collected 2,631 points 🤯

Congrats to all and thank you for being an essential part of the Airtable Community!

Top Solution Authors 🧠

• 1. @TheTimeSavingCo and @ScottWorld - 5 Answers Given
• 1. @DisraeliGears01 - 3 Answers Given
• 1. @Mike_AutomaticN, @Dodelita, and @nroshak - 1 Answer Given
• *Shout out to @Dodelita who found the solution to their problem and came back to the community to share it!

Top Replies 📨

• 1. @Mike_AutomaticN - 125 Replies Authored
• 1. @TheTimeSavingCo - 85 Replies Authored
• 1. @ScottWorld - 78 Replies Authored
• 1. @Flow Digital - 26 Replies Authored
• 1. @DisraeliGears01 - 23 Replies Authored
• *Congrats to @Flow Digital on joining the Top Contributors for the first time this month!

Top Liked Authors 👍

• 1. @Mike_AutomaticN - 54 Likes Received
• 1. @ScottWorld - 48 Likes Received
• 1. @TheTimeSavingCo - 40 Likes Received
• 1. @DisraeliGears01 - 17 Likes Received
• 1. @Philip_Ade - 4 Likes Received
• *Congrats to @Philip_Ade on joining the Top Contributors this month!

Top of the Leaderboard 📊

• 1. @Mike_AutomaticN - 779 Points Earned
• 1. @ScottWorld - 731 Points Earned
• 1. @TheTimeSavingCo - 700 Points Earned
• 1. @DisraeliGears01 - 249 Points Earned
• 1. @Flow Digital - 172 Points Earned

ICYMI:

• 1. We recently launched Airtable’s first standalone product, Superagent.
  • Try it out and share your learnings in our new Superagent forum board!
  • Want to see how it works? RSVP for our upcoming AI User Group event on Feb. 12 with the people who actually built Superagent!
• 1. The Airtable Community Hackathon is back so sign up soon! Join other community members from 3/1-3/17 for some fun building under the theme "Let’s Play 🎲" — thanks to @Mike_AutomaticN for generously organizing this again

Spread the Community Love 💕

In the spirit of February, let's show appreciation for our fellow community members!

This month, challenge yourself to give a thumbs up to at least one helpful response, or better yet, answer a question from someone who needs your expertise. Head over to Unanswered Questions to give back to the community!

Sr. Program Manager, Community @ Airtable (DM me to discuss: Community, cute dogs, & SF Bay Area dining scene)

Launched: upload files in the scripting block!

We’re excited to announce a new input method for the scripting block: input.fileAsync! This enables script users to upload files, which the script can then use to do things like create or update records. If you’ve ever wanted to preprocess the data in your files before importing it to your base with the CSV or XML import block, you can now do so with input.fileAsync! Because you can access the file contents from inside the script, you could also do things like conditional record creation or custom fuzzy matching to update existing records. We’re excited to see how you can use this to empower your scripts! The returned value from the file input gives you access to the uploaded File itself, as well as the parsed contents of the file (if supported). Currently, parsing is automatically performed for .csv, .xls, .xlsx, .json, .xml, and .txt f

Hi everyone,

We’re rolling out three new AI improvements to make Omni feel much closer to where you already work in Airtable: interfaces, records, and comments.
Here’s what’s new:

• Open Omni from any interface or record detail
  You can now add an “Open Omni” button to any interface page or record detail with prewritten, custom Omni instructions. With one click, viewers can instantly perform complex actions like AI-driven data analysis, generating reports, or creating new records.

  Why this is useful

  • Builders can insert high‑quality, prewritten Omni instructions directly into an interface or record detail.
  • End‑users don’t have to write prompts or configure anything; they just click the button and Omni runs those instructions on the current record or view.
  • This gives teams consistent, repeatable AI output and makes it much easier for more people to benefit from Omni without needing to be prompt experts.

  How to use it

  • In an interface, add a new button element (or edit an existing one)
  • Choose “Open Omni” as the button action
  • Write your custom Omni instructions
  • Save and publish your interface
  • Viewers can now click that button to launch Omni with custom instructions from that page or record detail

• Omni, right where you’re working
  Omni is starting to appear in more places throughout Airtable. This means you don’t have to stop what you’re doing to go open Omni.
  You’ll now see Omni integration directly into common workflows like:

  • Writing or editing long text fields
  • Searching in a view or interface
  • Adding a new table
    For example, when you’re working in a long text field, Omni can help you draft, rewrite, or answer questions about the content as you type.

• Ask Omni questions about a comment thread
  For any record, you can now ask Omni questions specifically about the comments on that record.
  Examples of questions you might ask:

  • “What are the main decisions in this discussion?”
  • “Are there any open questions that still need follow-up?”
  • “Can you summarize the feedback from this thread in 3 bullets?”
    Omni will read the comment thread for that record and answer based on that discussion.

How to use it:

• Open a record with comments
• Ask Omni a question about the comment thread (e.g. “Summarize this conversation”)
• Omni will respond using the information in the comments for that record

We’d love your feedback
Whether you’re on an interface, inside a record, or in the middle of a comment thread, these features are all about making Omni easier to access in the exact moment you need it!
These updates are rolling out now, and we’re excited for you to try them. As always, let us know how they work for you and where you’d like to see Omni show up next.

AP@Airtable