AppsScriptPulse

Add-on, AI, Intermediate

Nano Steps, Giant Leaps: Exploring On-Device AI in Chrome for Workspace Editor Add-ons

Tags:
| | 0 Comments |

The landscape of what’s possible within the browser is quietly undergoing a significant shift, and for Google Workspace Add-on developers, this could be a game-changer. Chrome’s AI mission is simple yet powerful: to ‘make Chrome and the web smarter for all developers and all users.’ We’re seeing this vision begin to take shape with the emergence of experimental, built-in AI APIs in Google Chrome, designed to bring powerful capabilities using models like Gemini Nano directly to the user’s device.

There is a growing suite of these on-device APIs. This includes the versatile Prompt API, specialised Writing Assistance APIs (like Summarizer, Writer, and Rewriter), Translation APIs (Language Detector and Translator), and even a newly introduced Proofreader API. For many existing Workspace Add-on developers, some of the more task-specific APIs could offer a relatively straightforward way to integrate AI-powered enhancements.

However, my focus for this exploration, and the core of the accompanying demo Add-on being introduced here, is the Prompt API. What makes this API particularly compelling for me is its direct line to Gemini Nano, a model that runs locally, right within the user’s Chrome browser. This on-device approach means that, unlike solutions requiring calls to external third-party GenAI services, interactions can happen entirely client-side. The Prompt API provides web applications, including Google Workspace Editor Add-ons, with an open-ended way to harness this local AI for text-based generative tasks.

To put the Prompt API’s text processing abilities through its paces in a practical Workspace context, I’ve developed a Google Workspace Add-on focused on text-to-diagram generation. This post delves into this demonstration and discusses what on-device AI, through the versatile Prompt API, could mean for the future of Workspace Add-on development, including its emerging multimodal potential.

Why This Matters: New Horizons for Google Workspace Developers

Using an on-device LLM like Gemini Nano offers several key benefits for Workspace Add-on developers:

  • Enhanced Data Privacy & Simplified Governance:Sensitive user data doesn’t need to leave the browser, meaning no external API calls are made to third-party servers for the AI processing itself, which is a huge plus for privacy and can simplify data governance including Google Workspace Marketplace verification and Add-on data privacy policies.
  • Potential for Cost-Free GenAI (with caveats!): Client-side processing can reduce or eliminate server-side AI costs for certain tasks. Remember, “Nano” is smaller than its cloud counterparts, so it’s best for well-scoped features. This smaller size means developers should think carefully about their implementation, particularly around prompt design to achieve the desired accuracy, as the model’s capacity for understanding extremely broad or complex instructions without guidance will differ from larger models.
  • Improved User Experience & Offline Access:Expect faster interactions due to minimise network latency.

The biggest takeaway here is the opportunity to explore new avenues for GenAI capabilities in your Add-ons, albeit with the understanding that this is experimental territory and on-device models have different characteristics and capacities compared to larger, cloud-based models.

Proof of Concept: AI-Powered Text-to-Diagram Add-on

To showcase the tangible possibilities of on-device text processing, the demonstrator Add-on (available in the Nano-Prompt-AI-Demo GitHub repository) focuses on a text-to-diagram use case:

  • Users can describe a diagram in natural language (e.g., “flowchart for a login process”).
  • The Add-on then uses the Gemini Nano API via the Prompt API to convert this text description into MermaidJS diagram code.
  • It also allows users to directly edit the generated MermaidJS code, see a live preview, and utilise an AI-powered “Fix Diagram” feature if the code has errors.
  • Finally, the generated diagram can be inserted as a PNG image into their Google Workspace file.

Nano Prompt API Demo

This example illustrates how the Prompt API can be used for practical tasks within a Google Workspace environment.

Under the Bonnet: Utilising the Chrome Gemini Nano Prompt API for Text

The Add-on interacts with Gemini Nano via client-side JavaScript using the LanguageModel object in the Sidebar.html file. I should also highlight that all of the Sidebar.html code was written by the Gemini 2.5 Pro model in gemini.google.com, with my guidance which included providing the appropriate developer documentation and this explainer for the Prompt API.

The Add-on’s core logic for text-to-diagram generation includes:

  • Session Creation and Prompt Design for Gemini Nano:A LanguageModel session is created using LanguageModel.create().
  • Generating Diagrams from Text: The user’s natural language description is sent to the AI via session.prompt(textDescription).
  • AI-Powered Code Fixing: If the generated or manually entered MermaidJS code has errors, the faulty code along with the error message is sent back to the model for attempted correction.

Given that Gemini Nano is, as its name suggests, a smaller LLM, careful prompt design is key to achieving optimal results. In this demonstrator Add-on, for instance, the initialPrompts (system prompt) play a crucial role. It not only instructs the AI to act as a MermaidJS expert and to output onlyraw MermaidJS markdown, but it also includes two explicit examples of MermaidJS code within those instructions.

Providing such “few-shot” examples within the system prompt was found to significantly improve the reliability and accuracy of the generated diagram code from text descriptions. This technique helps guide the smaller model effectively.

Navigating Experimental Waters: Important Considerations (and Reassurances)

It’s important to reiterate that the majority of AI APIs are still experimental. Functionality can change, and specific Chrome versions and flags are often required. I recommend referring to official Chrome AI Documentation and Joining the Early Preview Program for the latest details and updates.

Before you go updating your popular production Google Workspace Add-ons developers should be aware of the current system prerequisites. As of this writing, these include:

  • Operating System: Windows 10 or 11; macOS 13+ (Ventura and onwards); or Linux.
  • Storage: At least 22 GB of free space on the volume that contains your Chrome profile is necessary for the model download.
  • GPU: A dedicated GPU with strictly more than 4 GB of VRAM is often a requirement for performant on-device model execution.

Currently, APIs backed by Gemini Nano do not yet support Chrome for Android, iOS, or ChromeOS. For Workspace Add-on developers, the lack of ChromeOS support is a significant consideration.

However, Google announced at I/O 2025 in the ‘Practical built-in AI with Gemini Nano in Chrome’ session that the text-only Prompt API, powered by Gemini Nano, is generally available for Chrome Extensions starting in Chrome 138. While general web page use of the Prompt API remains experimental this move hopefully signals a clear trajectory from experiment to production-ready capabilities.

Bridging the Gap: The Hybrid SDK

To address device compatibility across the ecosystem, Google has announced a Hybrid SDK. This upcoming extension to the Firebase Web SDK aims to use built-in APIs locally when available and fall back to server-side Gemini otherwise, with a developer preview planned (see https://goo.gle/hybrid-sdk-developer-preview for more information). This initiative should provide a more consistent development experience and wider reach for AI-powered features.

A Glimpse into the Future: Empowering Workspace Innovation

On-device AI opens new opportunities for privacy-centric, responsive, and cost-effective Add-on features. While the demonstrator Add-on focuses on text generation, the Prompt API and the broader suite of on-device AI tools in Chrome offer much more for developers to explore

Focusing on Unique Value for Workspace Add-ons

It’s important for developers to consider how these on-device AI capabilities—be it advanced text processing or new multimodal interactions which support audio and image inputs from Chrome 138 Canary—can be used to extend and enhance user experience in novel ways, rather than replicating core Gemini for Google Workspace features. The power lies in creating unique, value-added functionalities that complement native Workspace features.

Explore, Experiment, and Provide Feedback!

This journey into on-device AI is a collaborative one and Google Workspace developers have an opportunity to help shape on-device AI.

  1. Explore the Demo: Dive into the Nano-Prompt-AI-Demo GitHub repository to see the text-to-diagram features in action.
  2. Try It Out: Follow setup instructions to experience on-device AI with the demo, and consider exploring multimodal capabilities for your own projects by referring to the latest Early Preview Program updates.
  3. Provide Feedback: Share your experiences either about the example add-on or through the Early Preview Program.

I hope you have as much fun working with these APIs as I have and look forward to hearing how you get on. Happy Scripting!

Official News, Intermediate, Sheets

Simplify Google Sheets Table Management with New API Support

Tags:
| | 3 Comments |

Following the improvements made to tables in Google Sheets in March and April, we’re excited to introduce API support for tables. Now, users will be able to take basic actions to create and modify tables via the Sheets API.

Following enhancements to Google Sheets tables last year, Google recently highlighted an update for developers: the Sheets API now supports tables. This is great news for the Google Workspace developer community, as it allows for direct programmatic creation and modification of tables, moving beyond previous reliance on workarounds.

For a while, developers have found clever ways to interact with table-like structures, such as Kanshi Tanaike’s notable 2024 solution using a mix of Apps Script and Sheet formulas. While these methods were very clever, the new, direct API support offers a more robust and straightforward way for interacting with tables in Google Sheets. For Google Apps Script users, for now this will require using the Google Sheets Advanced Service to call these new table methods, as direct integration into the SpreadsheetApp service hasn’t been announced at this time.

Key API Capabilities for Tables:

The Sheets API now lets developers:

  • Add Tables: Create tables with defined names, ranges, and specific column properties (like ‘PERCENT‘ or ‘DROPDOWN‘ with validation).
  • Update Tables: Modify table size (add/remove rows/columns), and toggle table footers. The API also provides methods like InsertRangeRequest and DeleteRangeRequest for more granular control.
  • Append Values: Easily add new rows to the end of a table using AppendCellsRequest, which intelligently handles existing data and footers.
  • Delete Tables: Remove entire tables and their content (DeleteTableRequest) or just the formatting while retaining data (DeleteBandingRequest).
  • Utilise Column Types: Work with various column types including numeric, date, dropdown, smart chip, and checkbox.

For further details, the official Google Workspace Updates blog and the Sheets API developer documentation on tables are your best resources.

Solutions, Slides, Intermediate

Enhanced Text Replacement with Styling in Google Slides using Google Apps Script

Tags:
| | 0 Comments |

This is a sample Google Apps Script designed to replace all instances of specific text within a Google Slides presentation, while simultaneously applying a desired text style. The built-in Presentation.replaceAllText() method within the Google Slides service is limited; it efficiently replaces text strings but lacks the functionality to modify text formatting during the replacement process. This limitation poses a challenge when aiming for styled text replacements. This report presents a detailed script solution that overcomes this constraint.

Have you ever needed to replace text across your Google Slides presentation but also wanted to apply specific formatting to the new text at the same time? The standard replaceAllText() method in Apps Script is handy for bulk text replacement, but it falls short when you need to control the styling – like font, size, or colour – during the replacement process.

Community contributor Kanshi Tanaike has developed a clever solution to overcome this limitation. Tanaike has shared a Google Apps Script function that not only finds and replaces text throughout all elements in your slides (including shapes, tables, and grouped objects) but also applies your desired text styles simultaneously.

The script works by iterating through the elements on each slide. When it finds the text you want to replace, it uses TextRange methods to perform the replacement and apply the specified formatting attributes, such as font family, size, colour, bold, italics, underline, and more.

This approach provides significantly more control than the built-in method, allowing you to ensure that automatically replaced text matches the exact styling you need for visually consistent and polished presentations. Tanaike’s post includes the full script, configuration details for specifying the text and styles, and sample slides showing the results.

Source: Enhanced Text Manipulation in Google Slides using Google Apps Script

Solutions, AI, Intermediate

Iterative Image Generation with the Gemini API and Google Apps Script

Tags:
| | 1 Comment |

Image credit: Kanshi Tanaike

Gemini API now generates images via Flash Experimental and Imagen 3. This report introduces image evolution within conversations using Gemini API with Google Apps Script.

The Gemini API recently gained the ability to generate images. Taking this a step further, Kanshi Tanaike has explored how to create evolving images within a conversation using Google Apps Script.

Often, you might want to generate an image and then iteratively add or modify elements in subsequent steps. Kanshi’s approach cleverly uses the chat functionality of the Gemini API (gemini-2.0-flash-exp model). By sending prompts sequentially within a chat, the API uses the conversation history, allowing each new image to build upon the previous one. This enables the generation of images that evolve step-by-step based on your prompts, as demonstrated in the original post with examples like drawing successive items on a whiteboard.

This technique is particularly useful because, as noted in the post, using chat history provides better results for this kind of sequential image generation compared to generating images from isolated prompts.

Kanshi Tanaike’s original post includes a detailed explanation, setup instructions (including API key usage and library installation ), and complete sample code snippets that you can adapt for your own Google Workspace projects.

Source: Generate Growing Images using Gemini API

Solutions, Sheets, Intermediate

Streamlining Conditional Formatting in Google Sheets with Apps Script

Tags:
| | 0 Comments |

I’ve created a small (pseudo) class that more easily clears and creates conditional formatting rules in a Google Sheet tab with Google Apps Script. Why? Well in Google Apps Script, conditional formatting rules are all or nothing. You can only ever set, get or clear ALL rules in a specified Google Sheet tab.

Conditional formatting in Google Sheets can be a powerful tool. However, Google Apps Script’s native setConditionalFormatRules() method replaces the entire set of rules, requiring the retrieval and reconstruction of the complete rule array to add, modify, or remove a single rule. This can be cumbersome and inefficient.

Fortunately Scott Donald has developed Range_ConditionalFormatting(), a valuable utility that simplifies conditional formatting management. This includes a SetRule method that allows you to add new rules without overwriting existing ones, and the position parameter provides precise control over rule order, which is crucial as conditional formatting rules are applied sequentially.

Scott’s post includes all the code you need to get this working in your own project along with a number of example snippets. This makes managing conditional formatting much more efficient and manageable.

Source: Clear and Set Conditional Formatting Rules to a Specific Range in Google Sheets with Apps Script – Yagisanatode

Library, Solutions, Gmail, Intermediate

Create Responsive Emails Easily with Google Apps Script and MJML

Tags:
| | 0 Comments |

Today I had the task of implementing a newsletter for internal updates and decided to use Google Apps Script since I was already using it for managing the project data. Based upon past experiences with emails using HTML I need this area was full of landmines and I didn’t want to navigate through it. 💣

So I decided to use MJML with Google Apps Script.

Sending emails using Google Apps Script is a common task, however, creating HTML emails that render consistently across different email clients and that look visually appealing can be challenging.

Justin Poehnelt’s post on DEV Community, “Using MJML in Google Apps Script to Send Beautiful Emails,” offers a solution to this problem. MJML is a markup language that makes it easy to create responsive HTML emails. It removes some of the complexities of HTML email development, allowing users to focus on the content of their emails.

In the post, Justin explains how to use MJML with Google Apps Script to send beautiful, responsive emails. He also mentions that he has published a library, MJMLApp, that “hides the gnarly bits” of using MJML with Google Apps Script. This library is available on GitHub in the mjml-apps-script repo where you can find the library ID and basic usage information.

Source: Using MJML in Google Apps Script to Send Beautiful Emails

Solutions, AI, Intermediate

‘AI Agents’ in Google Apps Script: Automate Google Workspace with Natural Language

Tags:
| | 0 Comments |

Imagine that you write in plain English what you want to do in Google Workspace (eg. workflows) and it happens just like magic. Insert text prompt, Gemini will generate the code for you and run it immediately. A dream? No, reality, thanks to my conceptual and practical idea of how to implement AI Agents in Google Apps Scripts to leverage the V8 runtime.

Ivan Kutil has explored the concept of AI Agents in Google Apps Script, enabling Google Workspace automation via plain English descriptions. Users describe their automation needs in natural language, which is then processed by Gemini API to generate the necessary code. The generated code is then executed in your Google Apps Script project.

Ivan’s solution uses the gemini-2.0-flash-thinking-exp-01-21 model, an experimental model within Vertex AI specifically designed to reveal its ‘thinking process’, resulting in more reliable code generation. The enhanced reasoning capabilities of this model are particularly beneficial for complex automation tasks, making it a powerful tool for Google Workspace customisation.

To ensure that the agent is doing the right thing, the clever bit is you can test the execution via a dry-run, where the code created with Gemini Flash Thinking is sent to an internal ‘Tester’ agent, which uses Gemini to comment on the code and summarises it in a log. It’s important to review the script before running it, as Ivan accepts no responsibility for the results of the script. Another nice feature is the generated code is stored in the Cache, so after running a dry-run and then a run, the same version will be executed within the Cache limit (currently set to 5 minutes).

This solution, which mirrors Gemini for Workspace’s ability to generate and execute basic Python code, suggests a future where Gemini for Workspace could write and execute Apps Script code for basic tasks. This has the potential to transform how users interact with and automate their Google Workspace environments.

If you are interested in a version of Ivan’s solution that incorporates my GeminiApp library, follow this link. For additional information on Ivan’s solution including setup instructions follow the source link.

Source: Create AI agents in Google Apps Script with Vertex AI and Gemini

Advanced, Intermediate, AI, Sheets

How Apps Script Became the Ultimate LLM Fine-Tuning Tool

Tags:
| | 0 Comments |

If you have domain-specific knowledge that you want an LLM to leverage, you probably have a use case for fine-tuning. Fine-tuning can significantly improve how well the model understands and responds to your queries, whether it’s legal documents, medical texts, financial reports, or niche industry data.

The most crucial step in this process is structuring your data correctly. If your dataset is well-organized and formatted properly, the rest of the workflow becomes much more manageable. From there, it’s just a matter of setting up a few configurations and automating parts of the process with Apps Script. That’s where things get interesting and surprisingly efficient.

Source: How Apps Script Became the Ultimate LLM Fine-Tuning Tool

Solutions, Sheets, Intermediate

Streamline Your Google Sheets: Automate Row Archival with Google Apps Script

Tags:
| | 0 Comments |

Archive Google Sheet Data with Google Sheets API Advanced Service in Google Apps Script

Keeping your Google Sheets organised can be a chore. A recent tutorial by Scott Donald shows you how to automatically archive old rows based on multi-column parameters using Google Apps Script and the Advanced Sheets API, making data management easier and more efficient. This post highlights Scott’s approach to scripting a solution, including how to set up the Sheets API, the main components of the script, and potential applications.

As always Scott packs in a lot of useful tips and guidance; in particular, the tutorial highlights how to archive data using just five API calls, potentially making it faster than the standard SpreadsheetApp approach. Scott also details how to modify the script to suit different processes and includes details on his SsReq class. It provides a structured way to perform common operations like retrieving data, finding rows based on criteria, copying rows, appending rows, and removing rows, making it a great addition to your personal Apps Script toolbox.

For detailed explanations, code examples, and helpful tips, consult the complete tutorial.

Source: Creating a Google Sheets Row Archiver with Google Sheets API Advanced Service and Apps Script – Yagisanatode

Solutions, AI, Sheets, Intermediate

Bulk Image Generation with Imagen 3, Sheets, and Apps Script

Tags:
| | 0 Comments |

Discover how to combine Imagen 3 and Google Sheets for rapid image creation. Automate your workflow and generate visuals in bulk.

Have you ever wished you could create a bunch of images without the hassle of typing in each prompt one by one? Well, Stéphane Giron has shared a clever solution using Google’s Imagen 3, Google Sheets, and Apps Script to streamline this process. While Gemini for Workspace is rolling out to more users and includes Imagen 3 for image creation in apps like Slides and the Gemini side panel, it doesn’t offer an easy way to create images in bulk. That’s where this method comes in. Instead of making images one at a time, this approach allows you to generate multiple images at once, saving you time and effort.

To get started with this method, you’ll need a Google Cloud Project and creating a service account (see the Build an AI slides reviewer with Gemini tutorial for instructions on setting this up). Once that’s set up, you create a Google Sheet with a column for your text prompts, and another for the links to the generated images. The images are automatically saved into a specific folder in your Google Drive.

The real magic happens with Apps Script. It uses Vertex AI to connect with the Imagen 3 model. The script reads each prompt from your sheet, sends it to Imagen 3 to create an image, and then stores the image in Google Drive. It also helpfully adds the image’s link back into the Google Sheet.

Check out the source post for the required code and instructions.

Source: Imagen 3 + Google Sheets + Google Apps Script: The secret to effortless bulk image generation