tr Skip to content

Create Google AI text for new Airtable records and update the record with AI generated text

When a new record is created in Airtable, Google AI generates text from a prompt built on that record, and FlowMattic writes the result back into a field on the same record.

Airtable Google AI

3 steps Setup ~5 min Used on 1.7k sites Free to import

The Create Google AI text for new Airtable records and update the record with AI generated text workflow on the FlowMattic canvas, with 3 steps across Airtable, Google AI
The workflow as it appears in the builder after import. Each step opens for editing.

What this workflow does

Airtable is often where product lists, content ideas or customer notes are collected, and many of those records need a bit of writing: a description, a summary, a short reply. This workflow asks Google AI for that text as soon as a record is created and puts it straight back into the record, so the base fills itself in.

The Airtable trigger fires when a new record is created in the base and table you connect, and passes the record's fields and ID on. The Google AI Generate Text step then produces text from your prompt. It ships unmapped, so after import write the instruction and map the record's fields into it, for example "Write a two-sentence product description for" followed by the product name and features.

The final Airtable step updates an existing record. It ships unmapped as well. Map the record ID from the trigger, so the update goes to the record that started the run, and map the Google AI response into the field that should hold it, such as a Description or Summary field.

Every new record starts a run, so records created empty or in bulk get text too. Create a test record and check Task History for the prompt Google AI received and the text it returned.

Product descriptions for a catalogue base

An online shop adds products to Airtable with a name and a few features, and each record gets a first-draft description the team can polish.

Summaries of customer feedback

A product team logs feedback in Airtable, and Google AI writes a one-line summary on each record so the list is quick to scan.

Social captions from a content plan

A marketer records each planned post's topic in Airtable and gets a suggested caption written into the record for review.

How this workflow runs

What happens at each step once the workflow is on, and what you need before you import it.

  1. Step 1Trigger
    Airtable New Record

    Starts a run when a new record is created in the Airtable base and table you connect. The record's fields and its ID are passed to Google AI and to the update step.

  2. Step 2Action
    Google AI Generate Text

    Generates text with Google AI from the prompt you write. The step ships unmapped: add the instruction and map the new record's fields into it so the output fits that record.

  3. Step 3Action
    Airtable Update Record

    Writes the AI text back to Airtable by updating a record. Nothing is mapped, so map the record ID from the trigger to target the same record, and put the Google AI response into the field you set aside for it.

What you need

  • FlowMatticCore
  • Airtable AccountAccount
  • Google AI AccountAccount

After importing, map your own data. To keep the template universal, not every step is pre-filled. Open each step in the builder and connect your accounts and fields (channels, lists, sheets, recipients) before you switch the workflow on.

Make it yours

Changes worth making after you import it.

  • Create a dedicated field such as AI Draft for the generated text, so the AI output never overwrites fields your team typed in.
  • Put a Filter between the Airtable trigger and the Generate Text step that continues only when the field your prompt relies on is not empty. Records created blank then get no AI text. Pick your own field.
  • Ask for a fixed length or format in the prompt, such as two sentences or three bullet points, so the generated text fits the Airtable field.

Questions about this workflow

Does the Google AI text go into the same Airtable record?

Yes, once you map the record ID from the trigger into the Update Record step. The template leaves that step empty, so set the ID and the field for the AI response after import.

Do I need a Google AI account to use this Airtable workflow?

Yes. The Generate Text step runs through your Google AI connection, which you add in that step after import.

Will updating the record with AI text start another run?

No. The trigger reacts to newly created records. The update changes an existing record, which isn't a new record.

What happens to records that were already in the Airtable table?

They're left as they are. Runs start only for records added once the workflow is active.

Import this workflow into your WordPress site

Download the JSON, import it from the Workflows screen and connect your accounts. Every run stays on your server, with no per-task fees.

30-day money-back guarantee Unlimited workflows and runs Self-hosted

Customers who run it every day

Rated 4.8 out of 5 by customers
Read more reviews

Flowmattic is a noteworthy option for businesses looking for a self-hosted alternative to Zapier. With its user-friendly interface and a strong set of features, it is a top pick for those in need of a reliable WordPress automation solution.

Creative-Minded Multimedia

The main advantage of the plugin that it can turn your WordPress installation into a powerhouse, just imagine that you can replace all other integration with only this one.