Extending Google Workspace Flows with Custom Steps using Google Apps Script

Google Workspace Flows is currently available as part of the Gemini Alpha program for Google Workspace customers. If you don’t have access to Workspace Flows you will need to request access via your Google Workspace Administrator.

As developers, we often find ourselves building complex automations to glue different services together. But with the introduction of Google Workspace Flows, Google is handing some of that power directly to business users, allowing them to string together tasks—like summarising emails or posting to Chat—without writing a single line of code.

But where does that leave us? Right in the driver’s seat.

While Flows provides a “no-code” interface for users, it offers a robust “code” backend for us. Developers can extend the platform by building custom steps, in Google Apps Script. These steps act as reusable building blocks that users can drop into their flows to perform specific, business-critical tasks that aren’t available out of the box.

If you have an existing Google Workspace Add-on, you can even extend its functionality to include these Flows steps. Since Google Workspace Flows is currently part of the Gemini Alpha program, custom steps are intended for internal use and testing within your own Google Workspace organization rather than public distribution. You can deploy them as test deployments or private add-ons for your domain, but a public listing is not yet supported.

Here is a high-level overview of how it works and where to find the documentation to get started.

The Anatomy of a Step

Building a custom step in Apps Script isn’t too dissimilar from building an Editor Add-on, but there are specific architectural differences to be aware of. A step essentially consists of three parts:

1. The Definition (Manifest): You define the step’s identity, required inputs, and expected outputs in the appsscript.json file.
2. The Configuration (UI): You build a card interface (using CardService) that allows the user to configure the step when they add it to their flow.
3. The Execution (Logic): You write the actual function that processes the inputs and returns the outputs.

Key Capabilities

The documentation provided by Google is comprehensive. Here are the key areas you should explore to understand what is possible:

1. Configuration Cards & Variables
Unlike a static settings page, configuration cards in Flows are dynamic. You can build cards that accept input variables from previous steps. For example, if a user has a “New Email” trigger, your step can ingest the email body as a variable.

• Read more: Build a configuration card

2. Passing Data
Your step doesn’t just run in isolation; it talks to the rest of the flow. By defining output variables, your script can return data (like a calculated value or a file ID) that subsequent steps can use.

• Read more: Pass data between steps

3. Robust Validation
To ensure users don’t break your script with bad data, Flows supports two types of validation. You can use Client-side validation (using Common Expression Language, or CEL) for instant feedback on the UI, or Server-side validation for complex checks against external databases.

• Read more: Validate an input variable

4. Handling Complexity
For more advanced use cases, simple strings and integers might not be enough. The platform supports Custom Resources for grouping complex data structures (like a CRM lead object) and Dynamic Variables for inputs that change based on context (like selecting a specific question from a Google Form).

Getting Started

If you are part of the Gemini Alpha program and want to get your hands dirty, the best place to start is the Quickstart guide. It walks you through building a simple calculator step that takes two numbers and an operator to output a result.

• Start here: Quickstart: Build a calculator step
• Deep dive: Extend Google Workspace Flows Overview

It is exciting to see Google offering a bridge between the ease of no-code and the power of Apps Script.