It has finally happened! Bot Bender 2.0 is now available for installation from the Google Workspace Marketplace. In this post, I will walk you through the steps needed to get to the marketplace.
We’ve shared a couple of journeys to Google Workspace Marketplace publication but this is the first I’ve seen for publishing a Google Chat App. For people who have gone through the process it’s probably a familiar story of back and forth with the Marketplace review team.
In this post Anton Shevchuk shares how his Chat App received multiple rejects due to issues with the location of the support/privacy pages. The moral of the story is to be persistent, and don’t hesitate to push back if you believe the reviewers are mistaken. The post from Anton also outlines the other steps involved, including connecting the Google Workspace Marketplace SDK and configuring app visibility settings.
You can apply to join the Google Workspace Developer Preview Program to get early access to certain features. Features in developer preview have already completed early development phases, so they’re ready for implementation. This program gives you the chance to shape the final stages of feature development with feedback, get pre-release support, and have your integration ready for public use on launch day.
The Google Workspace Developer Preview Program (DPP) gives you early access to new features. If you are developing Google Workspace products and solutions, it’s a great way to stay ahead of the curve and provide feedback before feature release. Anyone can apply to join the DPP, just follow the source link, but note that you can’t enroll with a gmail.com account.
New Google Chart Card UI has just been added for buttons, chips, collapsible sections, and overflow menus. These additions extend the capability of Google Chat, allowing the possibility for users to interact with external tools and services without leaving the chat and continually having to context switch.
The public documentation page includes a list of all active developer previews. While these pages don’t offer visuals of the features, existing DPP members received a nice set of visuals in the email update. This example includes chips and a customizable control button for a collapsible section:
I’d highly recommend registering for the DPP so you can see what is coming in Google Workspace.
To subscribe to events using Apps Script, you can now use the Advanced Google Workspace Events service.
In the May 02, 2024 Google Apps Script release notes it was announced that a new Advanced Google Workspace Events service is available to let developers use the Google Workspace Events API directly in Google Apps Script. The Google Workspace Events API is a relatively new API, which was released to developer preview in January, 2024. The Google Workspace Events API uses a subscription model to handle resource changes. When you create a subscription, you specify the target resource (such as a Google Chat space or Google Meet meeting space) and the event types that you want to subscribe to. The API then sends notifications to your specified endpoint whenever an event occurs for that resource and event type.
In the case of the new Advanced Google Workspace Events service the linked documentation includes samples for using the new service with Google Chat. It’s worth noting that the Advanced Google Workspace Events service is designed specifically on managing subscriptions to events. While it lets you to control the flow of information and manage event subscriptions in your Apps Script projects, the actual processing and handling of event data occurs separately.
The linked documentation page provides sample code as well as outlines all the prerequisites.
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.
we’re making it easy for organizations to extend the power of their data and custom AI models by using Vertex AI with Workspace as a platform, enabling next-generation workflows that are built right into Docs, Gmail, and other Workspace apps
Google Cloud Next ’24 has just started but already a number of exciting product updates have been announced, including the indications of a possible deeper integration of Vertex AI into Google Workspace.
In one of our recent Pulse updates we highlighted Dialogflow CX and Google Chat API integration is now in Developer Preview. The reason I feel this is an important development is Dialogflow CX lies at the heart of Vertex AI Agent Builder (formerly Vertex AI Search and Conversation … formerly Gen App Builder).
Vertex AI Agent Builder lets developers easily build and deploy enterprise-ready gen AI experiences via a range of tools for different developer needs and levels of expertise — from a no-code console for building AI agents using natural language
This integration is significant because it addresses a key challenge I’ve experienced as a Vertex AI Agent Builder trusted tester. Previously, using Google Workspace data in your agents required moving it to a Cloud Storage bucket. The new integration potentially streamlines this process, allowing seamless access to your Workspace data.
This aligns with a broader trend I’m seeing at Google Cloud Next: the emphasis on custom Generative AI-powered agents. Gabe Weiss’s demo in this morning’s keynote showcased the potential of such agents to intelligently support users. Though details about the underlying technology were limited to Vertex AI Agent, the UI does hint at a gemini.google.com integration. You can see for yourself at the queued clip (this may change if Google trims the video).
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.
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.
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.
The Advanced Chat service lets you use the Google Chat API in Apps Script. This API allows scripts to find, create, and modify Chat spaces, add or remove members to spaces, and read or post messages with text, cards, attachments, and reactions.
There have been a number of updates to the Google Chat API summarised in the linked release notes page. A recent announcement which might interest Google Apps Script developers is the generally available of a new Advanced Chat Service. As noted in the official documentation:
The Advanced Chat service lets you use the Google Chat API in Apps Script. This API allows scripts to find, create, and modify Chat spaces, add or remove members to spaces, and read or post messages with text, cards, attachments, and reactions.
There are some perquisites to use the Advanced Chat service besides the usual turning it on before use, the main one being the requirement to use a standard Google Cloud console project rather than the default project created automatically.
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).
