Airtable AI assist field overview
  • 15 Nov 2023
  • 23 Minutes to read
  • Dark
    Light
  • PDF

Airtable AI assist field overview

  • Dark
    Light
  • PDF

Article Summary

This article covers the ins and outs of the AI assist field. We'll cover where this field might be useful to insert into your Airtable bases, how to set up the field, limitations and dependencies, as well as some of the common questions users have about this field type.

Note

The new AI assist field is currently in beta for select Airtable users and organizations. Learn more on how to gain access in the Introduction section below.

Introduction

Plan availability

Beta access is dependent upon plan type:

  • Legacy Enterprise, Enterprise Scale, and Business plan organizations should contact their account team to inquire about access. Access can then be further managed by admins in Admin Panel settings.

  • Team plan access is by waitlist only, sign up here

  • This beta is unavailable for Free, Legacy Plus, and Legacy Pro plan workspaces

Permissions

  • Owners/Creators - Can create and edit AI assist fields and generate outputs

  • Editors - Can generate AI assist field outputs 

Platform(s)

Web/Browser, Mac app, and Windows app

Related reading

Guide: Accelerate your work with Airtable AI

Why use Airtable AI assist?

Our approach to AI is that you shouldn't have to switch context by taking content out of Airtable, into an AI model, and then back into Airtable in order to gain more efficiency in your work. By its very nature, that is an inefficient process. That's why Airtable developed a new field type, AI assist, to conveniently plug AI into the data you already hold in Airtable. We believe that modern generative AI models have a massive opportunity to provide deep reasoning and creative starting points to help save you and your team time and resources.

Airtable AI can be added to any workflow and is flexible enough to advance critical steps across workflows in every team or department. 

  • Product teams can use AI to categorize customer feedback and generate product specs to speed up feature development. 

  • Marketing teams can use AI to generate creative briefs, generate SEO keywords, or draft blog posts. 

  • HR and finance teams can use AI to generate job descriptions, categorize budget spend, draft company memos, and more.

Setting up an AI assist field

In the walkthrough below we'll use the User Feedback base template to demonstrate a flow that summarizes user feedback as a singular category using the AI assist field. The goals of this flow are to:

  • Simplify user feedback to allow for easier tracking and categorization

  • Increase internal workflow efficiency by removing a step where an Airtable user would have instead needed to:

    • Create a new single select field in the Airtable base

    • Read through and monitor feedback in the "Additional notes" field

    • Categorize this feedback into a simplified category each time a new feedback request is received

This is just one example of the many ways that you can insert an AI assist field into an existing Airtable base to help save you and your team time and transform busy work into actionable work.

Step 1: Add an AI assist field

In an open base navigate to the table/view where you want to add a new AI assist field. Then click + to add a new field. From here, you'll find a list of field types that you can either search for by name or scroll through. Choose the AI assist option and move on to the next step.

Step 2: Choose a template or start from scratch

This will open the configuration window for the new AI assist field. Your first choice will be to Start with a template or Start from scratch. For our example, we will use a template.

After clicking Start with a template, another configuration window will appear. Airtable has created many templates for you to choose from that we have identified as common workflows where generative AI can be helpful. In this example, we will choose the Feedback categorization option under the product tab.

Note

If you are building a prompt from scratch, move on to Step 5 below. Steps 3 and 4 only relate to using prompt templates. If you need more guidance about how custom prompts work, then consult another section in the support article below.

Step 3: Configure the template (Templates only)

In order to have the AI assist field generate content, you'll need to configure a few pieces of information to help the AI models know where to look in your Airtable base as well as some additional instructions. This will vary by template, but you will one or more of the following:

  • Define the starting point - You'll need to choose the field or fields that will be utilized by AI assist. In certain cases, there will also be a box to add a comma-separated list of static values. 

  • Include additional fields - Sometimes, the template that Airtable provided might need more depth to allow the AI to process more information. In these cases, you'll want to add more fields of your choosing.

  • Add your own examples - Adding examples helps to structure and format the result that the generative AI produces. Good examples will help the AI models align more closely with your expectations of what the output should be.

  • Give any other instructions - All templates contain the option to give other instructions. This is your opportunity to add additional context that can further help the AI models with structure, formatting, style, language, and set boundaries for what the model should not do.

Note

Once the required fields for the template you are configuring have been designated, you'll see a preview of what the AI assist field will generate for the first record in the table that has those required fields filled in.

In our example, we chose the Feedback categorization template. This template only requires that we Define the starting point by choosing a field that contains the feedback and adding a comma-separated list of categories that the AI model will use for outputting content. You can see in the image below that:

  • The "Additional notes" long-text field is being used for the Feedback to be categorized

  • A comma-separated list of categories has been entered in the text box to help the AI assist field generate a category for the feedback.

  • There's an additional option to Give any other instructions but, for our purpose, this is not needed.

Once you've configured the template to your liking, click Use template. You can come back and edit the template later as discussed in the next step.

Step 4: Additional prompt editing (Templates only)

Once you have chosen to use a template, you'll notice two new options appear in the Prompt section of the field configuration window:

  1. Pencil icon - Use this to go back and edit the existing template's configuration. You can even try out another template if you are unsatisfied with the existing one.

  2. Break icon - CAUTION! Clicking this option will transform the existing template into a text box prompt. At this point, the prompt will function the same way as a prompt written from scratch. It's important to note that this option cannot be reversed. That is to say, you can't convert the text box back to the template configuration. It is, however, a good way to better understand how it is that a prompt might be written. We encourage you to experiment with this while you are testing out the AI assist field, but not in live bases with potential downstream effects.

For our example, we don't need to use either of these options at the moment.

Step 5: Preview the generative AI output

Once you've built out your prompt or template, you'll want to check the preview to see if the result is looking desirable. If not, it's time to go back and make some edits to the prompt or template to help the AI assist field achieve a more expected output. In some cases, the generated output might be something fairly simple, and in others, the output could be quite complex. It all depends on the workflow you are trying to achieve. 

Note

If a prompt requires certain fields to produce a result and the table contains no records that include those necessary fields' information, then Airtable won't be able to generate a preview. You'll see the error message No records found. To remedy this, check that at least one row in the table contains the necessary field information and create a "test" record if the table contains no records.

The preview box can be opened or collapsed by clicking on the caret icon (> or v) next to the Preview section. In our example of categorizing feedback, you can see that the first record in the table has been categorized as "Mobile app" in the preview. This looks like a good categorization after comparing it to the notes.

Step 6: Adjusting AI assist settings

There are some additional field settings that you can configure by clicking on the Settings tab in the AI assist field configuration window:

  • Model - There are two generative AI models to choose from, GPT-3.5 and GPT-4. We recommend you consult other resources if you want to dig into the differences between the two models, but briefly:

    • GPT-3.5 - OpenAI's first released model, and the model that currently powers ChatGPT. This model is faster, less expensive, and may be less accurate than GPT-4.

    • GPT-4 - OpenAI's most advanced model, which is more accurate than GPT-3.5. This model is slower, meaning that responses will take longer to generate. It is also more expensive and therefore much more limited in the number of calls you can make per day. GPT-4 is recommended for long-form writing such as marketing briefs, PRDs, and job descriptions.

  • Randomness (Temperature) - Randomness can help give certain outputs more variety on a scale from 0 to 1.0. The number can be adjusted in increments of .1 depending on your needs. Generally, you can expect the following behavior in records that contain the same or similar data:

    • 0 - Minimal to no variation in outputs. A good setting to use when you want to have expected, linear results in the output. 

    • .5 - Moderate variation in outputs. A good setting to use when you want some variation to the output of the AI assist field.

    • 1.0 - Maximum variation in outputs. The best setting for situations that can use more variation between output, even given the same inputs. This can be helpful when using the AI assist field to gain inspiration for writing.

  • Generate automatically 

    • This setting is only available when selecting the GPT-3.5 model setting and when the table that contains the AI assist field has 300 records or less.

    • When this option is turned on, AI assist will generate new outputs when the AI assist field's prompt sees that changes have been made in the base. To clarify, only changes that affect field(s) that the prompt is monitoring will cause a new output to be generated.

    • When this option is turned off a base user with Editor permissions or higher can Generate outputs manually. More on this in the next section.

Note

We cover more limitations to be aware of related to these settings in another section below.

Step 7: Create the AI assist field and generate

With the prompt written and settings configured, it's time to create the new AI assist field. Click the blue Create field button.

  • If the Generate automatically field setting is enabled, then you will begin to see each record in the table begin to populate with AI assist created content. Depending on the complexity of the prompt and the model you chose to use this may take a bit of time.

  • If the Generate automatically field setting is not enabled, then each record in the table will contain a button with the label Generate. This allows base users with Editor permissions or higher to either:

    • Generate outputs record by record on an individual basis, by clicking the Generate button.

    • Or generate outputs for every possible record (bulk generate) within the view that the user has open. To do this, click on the dropdown arrow next to the name of the AI field and then click the Generate content for xx records. If your table has more than 300 rows, you can do this generation in batches of 300 until all the rows in the table have been generated.

Note

If a record containing a field that is part of the AI assist prompt is required and empty, then you won't be able to generate an output for that record. In those cases, you'll see a message in the AI assist cell that says Required field is empty.

Understanding template builder vs. starting from scratch

Let's face it, AI is a new tool, and even folks with intimate knowledge of the ins and outs of what AI is don't know what AI is fully capable of. That's why Airtable built a suite of templates to help you become familiar with the AI assist field and quickly inject it into the workstreams you already have running in Airtable. For people who might have a bit more understanding of how to write an AI prompt from previous ChatGPT experiences, we also allow you to build a prompt from scratch. Learn more about each option below:

Start with a template

There are 5 categories of templates to choose from. We recommend testing out all of the different templates, especially if you are unfamiliar with AI and how prompt writing works. This will allow you to become more familiar with the differences and similarities between prompts to help you better understand what it is that AI models need in order to have a good starting point to work off of in Airtable.

  • General

    • Translation - Output text from a field in Airtable as translated text in the AI assist field.

    • Meeting summary - Output longer meeting notes as a succinct summary in the AI assist field.

    • Categorization - Configure a set of static, pre-defined categories and have the AI assist field categorize the content within another field in your table.

  • Product

    • PRD - Create formatted text for a product requirements document from multiple fields of information stored in Airtable.

    • Product launch brief - Create formatted text for a product launch brief from multiple fields of information stored in Airtable.

    • Feedback categorization - Configure a set of static, pre-defined categories and have the AI assist field categorize the feedback stored in another field in your table.

  • Marketing

    • Marketing brief - Use fields containing the product/feature name and the PRD for that feature to output a marketing brief in the AI assist field.

    • Campaign brief - Use fields containing the campaign name, description, and target audience or marketing brief to output a campaign brief in the AI assist field.

    • SEO keywords - Have the AI assist field create a list of keywords based on copy help within a field. You will set the number of words for the AI assist field to generate.

    • Tweet - Use a field containing a longer set of content that you want the AI assist field to summarize into a more succinct output of text.

  • UX Research

    • Sentiment analysis - Have the AI assist field use a field containing feedback as a source to be categorized by sentiment (positive, neutral, negative).

    • Research plan - Use fields in Airtable containing the research questions and objectives and then set a research type (Qualitative, Quantitative, Hybrid) to have the AI assist field output a research plan.

    • Feedback summary - Have the AI assist field summarize feedback from notes stored in Airtable during a research session by extracting specific insights.

    • Interview guide - Give the AI assist field a field containing a research plan and a length of time for the interview to output an interview guide.

  • Recruiting

    • Job description - Use fields in Airtable containing the job title, level/experience requirement, location, and any additional custom fields to create a job description in the AI assist field.

    • Outreach email - Have the AI assist field create a draft outreach email by using fields in Airtable that contain the job title, the candidate's current company, and their current role.

    • Search query - Give the AI assist field the job title, level, and location from other AIrtable fields and have it generate a list of keyword terms related to that job.

    • Candidate assessment - Have the AI assist field assess a candidate based on fields in AIrtable that contain their resume and the description of the job they are applying for.

Start a prompt from scratch

Writing a prompt from scratch requires a few things in order to be successful with the AI assist field in Airtable:

  • Giving the AI model a role is helpful (ex. "You are a product manager...")

  • Include Airtable fields in the prompt as needed to provide context for the request. When you include a field, provide the context of what kind of content the field is storing, such as: 

    • "Write an email that addresses the following customer feedback: {customer_feedback}"

    • or "Create a meeting summary based on the following notes: {Meeting Notes}"

  • You can use the blue + sign in the prompt window to add fields or begin typing the field name with a curly bracket {  in front of the name. Either option will open up a list of the fields you can use in the prompt. The field name will appear as a token in the prompt and will automatically update, even if the name of the field is changed later.

  • There are limits to be aware of as discussed in the next section below.

  • Give the AI model examples to work off of. When providing examples, make it clear at the end of the examples section what you want the model to do by prompting it specifically with the content you want it to ingest and what you want it to do.

Below are some examples of feedback and related sentiments that you'd output.

The feedback statements below are examples only.

Feedback: "This is the worst tent I've ever used."
Sentiment: Negative

Feedback: "This backpack is alright."
Sentiment: Neutral

Feedback: "I really love this sleeping pad."
Sentiment: Positive

Feedback: {customer_feedback}
Sentiment:
  • Define expected formats and length of the output if that is important for the result you want. 

  • Include "Do" and "Do NOT" statements to set boundaries for the AI model.

  • Remember that more specific prompts typically yield more specific outputs, while less specific prompts might result in more variation. You can use either method to acheive different results, but it's important to be intentional with your approach.

  • You can always go back and edit a prompt, but we strongly recommend that you save a previous prompt in case you want to revert back to it (paste it back into the prompt text box) while you are testing the AI assist field's output.

Dependencies and limitations

Airtable reserves the right to change these limits at any time throughout the beta program.

Daily limits per base

One "use" is counted when one cell is generating a response using AI.

  • GPT-3.5: 2,000 uses of the AI field with the model type set to GPT-3.5

  • GPT-4: 100 uses of the AI field with the model type set to GPT-4

Monthly limits

  • Monthly limits are set by the number of billable collaborators in your workspace or Enterprise, 10 million per user per month

  • An average request using GPT-3.5 might take between 1,000 - 10,000 credits but can vary.

  • You can see your monthly limits in Admin Panel or workspace settings.

Word limits

The total number of words in your query and response must be under a certain amount set by OpenAI. This includes the words in the fields referenced by your query. If you exceed these limits in your query, you will see an error message. If the AI's response exceeds the limits, the text will be truncated.

  • GPT-3.5: Up to ~12,000 words

  • GPT-4: Up to ~6,000 words

Auto-generation

The auto-generation setting on the AI assist field can be enabled in tables containing many records. However, if you do choose to "Generate automatically" on a table with thousands of records you are still limited by your daily and monthly limits. So, it's possible that some of the records will generate automatically, but others will eventually error out due to other limitations.

Bulk generation

In fields with auto-generation turned off, batches of 300 records can be generated at a time.

Enabling or disabling the AI feature

Once your workspace(s)/organization is part of the AI assist field beta, you may need to enable the feature at the Enterprise and workspace levels.

Team/Legacy Pro customers

  • The workspace ID(s) that you submitted in your Beta enrollment form will automatically be enabled with the feature.

    • If you want to turn the feature off, the individual who enrolled the workspace in the Beta will need to go to their account page, choose the workspace, and then locate the Workspace AI permissions section.

Business and Enterprise Scale customers

  • Global Admin Panel settings: To adjust this setting, admins should navigate to Settings > Integrations & development. Then look for the Block AI integrations section.

    • Block AI integrations

      • Leaving this setting ON (default) will globally prevent usage of AI models in all organization-owned workspaces.

      • Turning this setting OFF will allow admins to enable AI features to be turned on in one or more workspaces.

    • Allow AI integrations in organization-owned workspaces? 

      • Allow in all workspaces - Choosing this option will allow AI features to be enabled in all workspaces owned by the organization.

      • Allow only in selected workspaces - If this option is chosen, you can choose specific workspaces where AI features may be enabled.

    • For Business and Enterprise Scale customers, the settings below will only be visible if the Block AI integrations setting is set to OFF.

      • Individual workspace setting: Workspace owners will need to enable the AI feature in their workspaces once the global setting to block AI is turned OFF. From your account page, choose a workspace on the left side of the page where you have Owner permissions. Find the Workspace AI permissions section and then choose to either enable or disable AI features for all bases within the workspace.

Using AI assist in Airtable automations

With AI in Airtable Automations, you can combine the power of AI to build automated workflows such as:

  • Post to Slack when negative customer feedback is submitted

  • Summarize team updates and send an email every Monday morning

Automations that involve the AI assist action will incorporate at least three components, but can certainly contain more depending upon the complexity of the workflow that you are wanting to automate:

  1. An automation trigger that will tell Airtable to begin the automation and queue up the AI to run the prompt.

  2. A "Generate with AI assist" action step with the prompt, randomness, and model sections configured.

  3. One or more automation action steps that takes the content generated by the AI and does something with it - writes it to a record in Airtable, sends it in an email, posts it to Slack, etc.

Example: Send an email every Monday morning with a summary of all meetings last week

Note

You'll want to adjust any sample settings listed in the walkthrough below to match the field, view, and table names in your base. Use this example, just as a reference to think about the overall structure of building this type of automated workflow.

  1. Create a new automation with an "At a scheduled time" trigger set to run every 1 week on Mondays at 6:30 a.m. Test the trigger and move on once the trigger successfully tests.

  2. Next, we will use a "Find records" action to find only meetings from the past week. In this example, we will set the "Table" to be Weekly meetings, then "Find records based on" a View, and then set the "View" to be This past week's meeting.

    1. If you don’t already have a view set up like this in your base, then you will want to create a view that has filtering conditions set to only show meetings that occurred in the past week.

    2. Alternatively, you could also set conditions to accomplish this. Test this step until it tests successfully and then move on.

  3. Next, you'll add the Generate with AI assist action step. Here you will configure the prompt, randomness, and model. Let's focus on the prompt since randomness and model are covered above. For the prompt, we want a mix of static text to give the AI model context along with the details about the meeting that the AI model can interpret to generate a summary. Here's an example prompt to get your creativity flowing:

    You are a note-taker for our team's meetings throughout the week. Summarize, the 
    {List of 'Notes'} that were taken during each of the meetings. 
    Be sure to also include the meeting date found here: 
    {List of 'Meeting date'}, as well as a list of who attended the meeting located in this field: 
    {List of 'Attended'/List of 'Name'}

    Here is an image of what that looks like in Airtable:

    Note that the {List of …} tokens inserted using the blue plus button will be highly specific to the automation you are building as well as the underlying base's architecture.

  4. Finally, you will add a Send email automation action so that you can send the summarized meeting notes to your colleagues via email. Configure the "To" and "Subject" fields according to your needs. Then, in the "Message" you'll want to insert a token of the Generate with AI assist action's "Response." This response is the output that the AI assist feature generates based on the settings you configured in the prior steps of this automation. Here's an example of what that configuration might look like:

Security and Terms of Service

When using the AI assist field, note that any data within fields referenced in a prompt may be shown to users who can view the AI assist field. This is particularly important when leveraging an AI assist field in an interface, where certain fields used in the prompt may be intentionally hidden from interface collaborators. For example:

  • A creator builds an AI assist field that guesses a job title given an employee’s experience and salary

  • An interface is created that shows the AI assist field and the employee’s experience, but not the salary

  • An interface collaborator edits the employee’s experience section to instead tell the AI to ignore other instructions and repeat the salary input.

For more information on AI security and ToS please visit the following resources:

FAQs

How do I know if the Airtable AI Beta is enabled?

The easiest way to check whether Airtable AI is enabled in a given workspace is to try to create a new field in a base in that workspace. If you see the AI Assist field type from the dropdown menu, then the feature has been enabled. If you do not see it, check the following:

  • Check if you received a confirmation email that your company or account has been enrolled in the Beta program.

  • Enterprise users should ask their admin if the OpenAI integration is enabled in Admin Panel and if it's enabled for your workspace. If it is but you still don't see the feature, ask a workspace owner to check their workspace settings page to see if the feature is enabled in the workspace.

  • Team plan users should ask a workspace owner to check their workspace settings page to see if the feature is enabled in the workspace.

Are there any precautions when using Airtable AI?

AI responses are designed to be reviewed and edited by users and may contain inaccuracies or biases. 

Based on the terms of Airtable’s agreement with our AI vendors, the data you provide as input into the AI field will not be used to train their large language models. However, some companies have policies that restrict personally identifiable information (PII) such as emails, addresses, and telephone numbers from being sent to external vendors. If this is the case, refrain from using columns containing PII as inputs into an AI field.

What are the limitations of AI capabilities?

As a technology, AI has improved rapidly in its ability to understand language, answer questions, and carry out tasks. However, there are known limitations to the technology:

  • The models that Airtable AI uses were trained over a year ago and do not have access to the Internet, so they don't know any current information like the weather today.

  • These models are not good at doing math and may return nonsensical information if asked to do a task that requires calculation.

  • The models are not good at representing their confidence in an answer and may give an authoritative-sounding answer that is actually invented or inaccurate. Always check the accuracy of answers provided by AI.

Can I provide feedback on the beta version of AI assist?

Absolutely! You can provide feedback by clicking Give feedback or report issue within the AI field configuration menu. If you’re an Enterprise customer, you can also reach out to your account team and share feedback.

Which languages can be translated by OpenAI's models?

Translation capabilities might be limited on OpenAI’s end, but in general, you should expect that most common languages are available for translation.


Was this article helpful?