Answer questions based on Google Chat conversations with a Gemini API powered Chat app

This tutorial shows how to make a Google Chat app that answers questions based on conversations in Chat spaces with generative AI powered by Vertex AI with Gemini. The Chat app uses the Google Workspace Events API plus Pub/Sub to recognize and answer questions posted in Chat spaces in real time, even when it isn’t mentioned.

Here is another great tutorial from the Google Chat DevRel team, this time showcasing how the Google Workspace Events API and some new Google Chat UI elements can be used to turn a Chat space into a Gemini Pro powered knowledge base.

The sample solution will let you consume your Chat space message history into a Firestore database. The Chat app is an intelligent agent that can then monitor for new questions and make suggestions using Gemini to generate content based on the previous messages.

There is quite a bit of setup required as part of this tutorial, but it provides a solid foundation for quickly scaling this to your needs.  A demonstration and explanation of the sample app was given as part of the Google Chat apps and APIs: Build connected workflows for the hybrid workplace session at Google Cloud Next and a recording might be available soon!

Source: Answer questions based on Chat conversations with a Gemini AI Chat app  |  Google Chat  |  Google for Developers

I challenged Gemini to a game of battleship in Google Sheets. Here’s what happened 🚢


I tried to see if an AI that’s good at writing could also make smart moves in a game. I chose Battleship and set it up in Google Sheets to play against Gemini, the AI. The result was mixed. On one hand, yes, Gemini could play the game. It followed the basic rules and even managed to sink some of my ships. This was a big deal, especially since it took me a ridiculous number of days of coding to get there, and I nearly gave up at one point.

Dmitry Kostyuk has shared a blog post detailing his experiment pitting the Gemini API  against himself in a game of Battleship. As explained by Dmitry  while Gemini could follow the rules and even sink some ships, it needed help to avoid basic mistakes, revealing that AI still has room to grow in the realm of strategic games.

Dmitry built the game in Google Sheets and the source code is linked from the post. To guide Gemini, Kostyuk crafted detailed prompts outlining the game’s mechanics and decision-making logic. However, he encountered challenges due to Gemini’s limitations in providing strategic responses. Despite these hurdles, the project yielded valuable insights into prompting techniques for AI decision-making.

Source: I Challenged Gemini to a Game of Battleship. Here’s What Happened.

Boost your presentations with AI: A Google Apps Script tutorial for a Google Slides reviewer assistant

The Slides Advisor project is an open source, Google Workspace Add-On that uses artificial intelligence (AI) technology to review and give feedback on your presentations, whenever you need it. The project uses Google’s Gemini API image and text processing features to analyze your Google Slides against a set of guidelines and lets you know how you are doing against those guidelines. Even better, you can customize those guidelines to follow your organization’s recommendations, or remind you to improve your presentations based on rules you define for yourself.

We’ve all been there: scrambling to cram too much information onto a single slide. But what if you had an AI assistant to give your presentations a once-over?

The Slides Advisor is a free, open-source Google Workspace Add-on for Google Slides that uses the power of AI to analyze your presentations. It checks your slides against customisable guidelines, helping you ensure they’re clear, concise, and visually appealing.

Everything you need to get started is covered in the source post by Joe Fernandez and Steve Bazyl. One of the highlights for me is seeing how you can setup a service account to access the Gemini AI API with Google Apps Script. The post also covers how you can modify the prompt you use to get different responses from Gemini.

Source: Build an AI Slides Reviewer with Gemini  |  Google AI for Developers

Guide to completing Casa Tier 2 Security Assessment for Google Apps Script (and how to scan your Google Apps Script project for CASA)

If you want to publish your Google Apps Script project on the Google Workspace Marketplace, or if you already have an add-on or app on this marketplace and are using authorization scopes which are now restricted, you will have to go through a TIER 2 CASA security assessment.

Previously in Pulse we have shared ReDriveApp: A new Google Apps Script library to replace DriveApp and restricted scopes. If your Workspace Add-on still requires restricted scopes then you are going to have to think about the next steps and options. One option is going through the enhanced verification process, which requires a Cloud Application Security Assessment (CASA).

If you would like an overview of the process from a developer’s perspective you are in luck as Kelig Lefeuvre (Product Engineer at Scriptit & Folgo) has shared a guide specifically with Apps Script developers in mind. The article includes a number of useful tips and information about the review process which you won’t find in the official documentation.

As part of the CASA process Kelig recommends using the option to  you can submit bypass the Fortify scan and submit your own results. those results Kelig has also provided a second article with a step-by-step guide on ‘how to scan your Google Apps Script project for CASA’.

Source: Guide to Completing Casa Tier 2 Security Assessment for Google Apps Script & How to scan your Google Apps Script project for CASA

“going beyond basic bots” – Tutorial: managing projects with Google Chat, Vertex AI, and Firestore  

Image credit: CC-BY Google

This tutorial shows how to make a Google Chat app that a team can use to manage projects in real time. The Chat app uses Vertex AI to help teams write user stories (which represent features of a software system from the point of view of a user for the team to develop) and persists the stories in a Firestore database.

A recent episode of Totally Unscripted delved into “going beyond basic bots”, highlighting a couple of Google Chat app tutorials from the Google Developer documentation. One example, the “project management” Chat App, is worth mentioning in a Pulse post.

While this example uses Google Cloud Functions instead of Google Apps Script, as discussed in the episode, both approaches share many similarities. Deploying the project management app involves several steps, but I believe it’s a worthwhile investment to learn how to combine different solutions for building Google Workspace integrations. For developers seeking to expand their Google Workspace Add-on capabilities, this example serves as a valuable reference.

If you’re interested in using Firestore for data management but prefer Google Apps Script, Justin Poehnelt’s post on “Using Firestore in Apps Script.” is a great resource. This post provides a basic Firestore wrapper and links to other relevant Apps Script/Firestore libraries.

Source: Manage projects with Google Chat, Vertex AI, and Firestore  |  Google for Developers

Memoization in Apps Script with Cache Service

A generic Apps Script memoization function can be written to cache any function.

We’ve featured a couple of Apps Script optimisation techniques in the past. This example from Justin Poehnelt uses a technique found in many coding syntaxes of ‘memoization‘:

In computing, memoization or memoisation is an optimization technique used primarily to speed up computer programs by storing the results of expensive function calls to pure functions and returning the cached result when the same inputs occur again

For more background on when and why you might use ‘memorization’ you can read about Memorization [sic] in JavaScript. In the case of Google Apps Script developers have opportunities to integrate the built-in Cache Service and Properties Service to memorize function results in the context of the script, document or the user.

In the example provided in the source post by Justin it defaults to CacheService.getScriptCache() to store the memoized results but it would be easy to change this to CacheService.getUserCache() or CacheService.getDocumentCache(). With a little modification you could also include Properties Service.

To help you see how memoization works here’s a gist for both pure JavaScript and Apps Script techniques which you can copy and run in the Apps Script Editor. The results hopefully speak for themselves:

First run (cold start) and second run (warm start) with better performance for cached results first call

Source: Memoization in Apps Script | Justin Poehnelt

Semantic poetry with Google Apps Script – Using Semantic Retrievers and Attributed Question and Answer (AQA) in Google Workspace 

Image credit:

Image credit:

Imagine this: you recall a document about an intriguing subject but can’t pin down a specific term. It’s a common scenario where traditional search methods in Gmail or Google Docs often fall short, relying heavily on exact terms. Enter the realm of ‘semantic’ search, powered by advanced language models. ‘Semantic’ isn’t just a fancy word; it’s about understanding the meaning and context behind your words. Instead of a frustrating keyword hunt, these models interpret your descriptions, no matter how vague, to find that needle in the digital haystack.

“Code is Poetry” is the tagline popularised by the open-source blogging platform WordPress. In this post from Riël Notermans at ‘code is FOR poetry’. It’s well worth spending the time unpick what is happening in this tutorial. To help understand the implications I would also recommend watching this short video on the Google Workspace Developers channel where Riël explains how the technique can be used for other applications like knowledge bases.

Even if you are not interested in generating poetry it’s an opportunity to see how the Vertex AI Generative Language API can be used in Google Workspace, in this instance to generate text for a Google Doc using a corpus of data from your Google Drive. Follow the source link for the code and setup instructions.

Source: Semantic Poetry with Google Apps Script – Zzapps

‘Editing’ Microsoft files (Word, Excel, and PowerPoint) with Google Apps Script

In this report, I would like to introduce the sample scripts for using Microsoft Docs files with Document service, Spreadsheet service, and Slides Service of Google Apps Script.

Users have had the ability to edit MS Word, Excel and PowerPoint files directly in Google Drive for a number of years, Google making this the default behaviour in 2020. There aren’t currently any APIs or Apps Script services that enable you to edit these particular document types. This however hasn’t stopped Kanshi Tanaike for developing and sharing the MicrosoftDocsApp library which makes it possible to edit MS Word, Excel and PowerPoint files using the same methods as you would for Google Docs, Sheets and Slides.

The library is able to do this by converting the Microsoft files into the Google equivalent, before using the MS export options in Google Drive to replace the original files. This does create some limitations highlighted in the post. In particular, the original documents are overwritten and not directly edited which means any incompatible feature as part of the Microsoft to Google conversion will be lost. Regardless of these it’s a clever approach and might be useful for users who have to keep feet in both the Google and Microsoft worlds.

Source: Use Microsoft Docs Files (Word, Excel, and PowerPoint) with Document Service, Spreadsheet Service, and Slides Service of Google Apps Script

Google Apps Script Service Account impersonation without downloading private service account keys 

Avoid downloading private service account keys by using impersonation in Apps Script to obtain access tokens.

For Google Workspace Admins you can gain super powers (and super responsibility) using Google Cloud project service accounts. A common scenario is using service accounts with domain-wide delegation to make API calls impersonating Google Workspace users. With this you can do things like set a user’s Gmail settings including signatures, authenticate as a user in Google Chat and much more.

A quick way to use a service account is to download a JSON key. The challenge then given the potential capabilities of service accounts is securely storing the JSON key. A alternative approach, which is explained in this post by Justin Poehnelt, is using Apps Script to create and fetch a short-lived credential for your service account.

Short-lived credentials are highly recommended for applications requiring robust security and precise access control for service accounts, reducing the attack surface and the risks with accidentally exposing static secrets.

You can find out more include code snippets/setup in Justin’s post which also links to the support documentation.

Source: Apps Script Service Account Impersonation | Justin Poehnelt

Create a Google Chat Bot on your own data with Vertex AI Search and Google Apps Script

Create a Chatbot answering user questions based on your documents. RAG implementation with multiturn using Vertex AI Search and Apps Script

More GenAI, this time from Stéphane Giron looking at how Apps Script can be used to provide the glue for a Google Chat app powered by Vertex AI Search. In this example you can see how unstructured data like PDF documents can easily be uploaded to a Cloud Storage folder, which then become the knowledge base for the Chat app. The post includes a Google Apps Script snippet for sending messages to the Vertex AI Search API as well as instructions on how to create the chatbot, including how to import data into Vertex AI Search and how to integrate the chatbot into Google Chat.

The post is a great summary of what is possible when combining Google Chat and Vertex AI Search. If you are interested in finding out more about what is possible using Vertex AI Search with follow-ups Google provide a comprehensive guide.  

Source: Create a Google Chat Bot on your own data with Vertex AI Search and Google Apps Script