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.
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.
Quickly rename files in Google Drive with Apps Script and Google Gemini AI. The script will automatically rename the files with a descriptive name based on the image content.
Amit Agarwal is celebrating 20 years of ‘Digital Inspiration’, one of my go to resources for Google Workspace tech tips, tutorials and how-to guides. This recent post from Amit is a great example of the types of solutions he regularly shares. This time Amit is looking at how the Generative AI capabilities of the Gemini API can be used to help rename images in Google Drive. To achieve this there Amit shares handy Apps Script snippets for finding images in a Google Drive folder, grabbing the thumbnail images as Base64 encoded strings before calling the Gemini Pro Vision API to get suggested filenames with the prompt:
Analyze the image content and propose a concise, descriptive filename in 5-15 words without providing any explanation or additional text. Use spaces instead of underscores.
For this solution an API key for Gemini Pro Vision is generated in Google AI Studio (formerly MakerSuite). There are still geographic restrictions on access to Google AI Studio, but given Apps Script runs on Google servers once you have a API key you can continue to use it without having to proxy a location.
Image credit: Amit Agarwal
Adding image capabilities to the GeminiApp Apps Script library has been on my TODO. Now I’ve got an example to play with it should be easier to do .. thank you Amit Agarwal.
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 Zzapps.nl ‘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.
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.
Using Google Gemini API with Google Sheets to create personalized mail merges. An exploration in generative AI ‘function calling’
Google latest generative AI solution, Gemini, includes the capability to declare functions that the LLM can use in it’s response. The response includes the name of the function and the parameters the script needs to run the function.
The function isn’t executed by the LLM, but run with your code, which creates really interesting opportunities for Google Apps Script solutions. In particular, given user identity and authorisation is an integral part of Apps Script and how it integrates with other Google services it means solutions like personalised mail merges can be created in a couple of lines of code.
Follow the source link to find out more about function calling and exploring Gemini’s capabilities with data in Google Sheets.
This post describes how I designed and ran an audience survey with over 1,700 responses, using Google Forms, Sheets, Apps Script, and ChatGPT. I’ll show you the entire process from end-to-end, including how I:
Created a survey with Google Forms
Used Apps Script to automatically say thank you to 1,700 respondents
Analyzed the response data in Google Sheets
Used AI to help me understand the qualitative data
Presented the results in Google Docs
It’s rather fitting that the 1,000th Pulse post features content by the one and only Ben Collins! Back in late 2019, when I was thinking about creating a new community site for Google Workspace developers, Ben’s encouragement was the spark that ignited AppsScriptPulse.
And today’s post by Ben is a nice example of Apps Script’s power to automate repetitive tasks. As part of this he shows how to craft personalised “thank you” emails for Google Form survey response with Google Apps Script. Ben’s insights go beyond ‘thank-you’s as he outlines how he administers and analyses customer surveys, highlighting his design choices for Google Forms and data analysis using built-in Google Sheets functions.
To take things a step further, Ben also highlights how he used ChatGPT to categorize qualitative survey responses. With Google’s recent announcement of their new AI model, Gemini, which outperforms ChatGPT in a number of academic benchmarks, it would be interesting to see how these two platforms compare for this type of analysis.
Raising a glass (or an espresso :) to Ben and this 1,000-post milestone!
Imagen: An photo image which has a laptop with a spreadsheet application which appears to have rays of light
This is the second part exploring the GenAI capabilities in Google Sheets. In this part learn how you can make an Enhanced Smart Fill for Google Sheets
Google recently announced the latest feature for Duet AI for Google Workspace with Enhanced Smart Fill, which uses GenAI in Google Sheets to generate content based on data and the patterns entered by the user.
Continuing a previous post exploring the PaLM 2 API and LLM capabilities in Google Sheets, this post looks provides a Google Sheet template for experimenting with LLM prompts and spreadsheet data, including how you could make a ‘Enhanced Smart Fill’-like star review generator.
The post includes everything you need to get started, with you only having to make your own MakerSuite API key.
Imagen: photo looking over the shoulder of a robot looking at a screen with chat messages and hand writing notes
This tutorial shows how to make a Google Chat app that responds to incidents in real time. When responding to an incident, the app creates and populates a Chat space, facilitates incident resolution with messages, slash commands, and dialogs, and uses AI to summarize the incident response in a Google Docs document.
Paraphrasing noted Google Workspace Developer Expert, Romain Vialard, GenAI has made Google Chat apps a tangible prospect. This tutorial from the Google Developers site is a great example of how you can use Google’s Vertex AI with Google Chat. The tutorial will help you create a Google Apps Script powered Chat app that is able to summaries the messages in a Google Chat space.
There is a lot to take away from this example, but here are some of the headlines:
Setting a Google Cloud Project to use the new Google Chat Advanced Service for Apps Script
Setup and code for making calls to Google’s Vertex AI PaLM API (LLM) from Google Apps Script
Using the responses from Vertex AI to generate new assets.
There is a lot more you can do from this starting point, but hopefully it gives you a great starting point.
Building a Support AI Assistant for Google Workspace using Apps Script, Gen AI, and Google Chat.
This post from Stéphane Giron highlights one approach for improving responses from LLMs by integrating Google Custom Search Engine responses into the prompt. In this example Stéphane used Google Apps Script to power the AI Assistant, integrating with Google Chat for the user interface and Cloud Functions to reformat data.
This post is another example of the ‘power of the prompt’ and how LLM prompting strategies are a very effective way to utilise LLMs without having to ground or fine tune. If you are interested in understanding more here is a useful notebook produced by Michael W. Sherman which illustrates two powerful LLM prompting strategies: Chain of Thought and ReAct (Reasoning + Acting).
