Hi AppSheet Community,
We’re very excited to announce that Gemini in AppSheet Solutions is now Generally Available (GA)! This powerful capability allows AppSheet Enterprise Plus users to integrate Google’s Gemini directly into their automation workflows.
Why It matters: Supercharge your processes & build with confidence
With the new “AI task”, powered by Gemini, you can now automatically extract key information from uploaded photos, parse through complex PDFs, or categorize incoming requests based on their content – all within your existing AppSheet apps.
Here’s how this GA release of Gemini in AppSheet Solutions helps you:
- Automate smarter: Leverage Gemini to handle tasks like data extraction and categorization, freeing up your team for higher-value work.
- Keep humans in the loop: While Gemini accelerates tasks, you still control the workflow, easily incorporating human review steps where needed by your users, on mobile, web, chat, or Gmail.
- Easy to use (No Machine Learning Degree Required): Our pre-built AI capabilities work out-of-the-box. You can still provide additional context or instructions to tailor the results to your specific business needs, but getting started is simple.
- Build with confidence: We know that when configuring workflows, especially using AI, robust testing is crucial. You want to be sure you’re building the right solution for your teams. Our in-editor task testing lets you do just that. It allows you to tweak prompts and settings, see immediate results on sample data, and iterate much more quickly, building trust in your AI-powered automations before you deploy.
- Deploy AI safely & scalably: The AppSheet admin dashboard gives AppSheet admins visibility into Gemini usage within their organization. Furthermore, admins have control over which creators can use these Gemini features, ensuring governance and compliance.
How to get access & start building
You need to have an AppSheet Enterprise Plus plan.
The fastest way to try it out is to copy one of our sample apps showcasing the new AI task.
You can also start by building your own Gemini-powered automation:
- Open one of your existing apps in the AppSheet editor (or create a new one).
- Go to the Automation section of the editor and open or create a Bot.
- When adding a step to a process, you’ll now see the option to add an “AI Task”. Choose this to begin configuring your Gemini-powered step!
- Test your AI task using the task testing section (after saving your app). Input sample data to preview results, refine your prompts or settings, and use the ratings feature to help improve AppSheet’s answers in the future.
Use cases
Here are just a few ideas you can build and test today:
- Extracting information:
- Have technicians snap a photo of equipment; use the AI Task to automatically extract the Serial Number, Model Number, or Meter Reading into your AppSheet table.
- Process uploaded purchase orders (PDFs) or photos of shipping labels to extract PO numbers, company names, tracking numbers, or addresses.
- Extract key details like location, date, or names from incident reports
- Categorizing records:
- Analyze the description in employee expense submissions and automatically categorize them by type (“Travel”, “Meals”, “Software”, “Training”).
- Read incoming facility maintenance requests and categorize them by urgency (“High”, “Medium”, “Low”) or equipment type (“HVAC”, “Plumbing”, “Electrical”).
- Classify customer survey responses or feedback form submissions into types like “Bug Report”, “Feature Request”, “Positive Feedback”, or “Billing Inquiry”.
Learn more & share your feedback
- Sample App: Book library with Gemini
- Quick Start Documentation: Build your first AI-powered automation
- Creator Documentation: Use AI in automations
- Admin Documentation: Managing credits
We’re incredibly excited to see what you build.
Arthur on behalf of the AppSheet team
FAQ
What has changed since the Public Preview announcement?
For creators, there are a few updates:
- AI tasks now support more types of columns and in particular columns of REF types so you can leverage information in linked tables.
- You can now extract information not just from images and PDF files, but also from unstructured text data hosted in your data sources. In other words, you can select Text and LongText columns as inputs to the AI task.
- The quality of AI responses was improved for certain data types.
For admins, the AppSheet admin console now shows how many credits your organization is entitled to, how many have been consumed, how they are being used by your users and your applications. Admins could already limit which creators in their organization can leverage an AI task.
What are the licensing and pricing requirements?
First, your organization needs to have an AppSheet Enterprise agreement. With it, your organization automatically receives a pooled quota of credits, at no additional charge. In particular, no separate Google Workspace license is needed.
Second, creators need to have an AppSheet Enterprise Plus license to include AI tasks into their automation bots and apps. Then, running an AI task will consume credits from the organization’s pool. Credit consumption per task execution will vary based on the complexity of the task.
More detailed information at Managing credits (for AppSheet admins)
How can I see how many credits are consumed?
Only AppSheet admins can see their full quota of credits, the overall credit consumption, and how Gemini is used throughout the organization. They can do that via the AppSheet admin console.
Troubleshooting - Why won’t my AI task run?
There are a couple reasons why this can happen. First, you need to have an AppSheet Enterprise Plus license. Second, your AppSheet admin may have set up a policy to prevent the usage of Gemini, in which case you should see an error message in the AppSheet editor. Beyond that, you should be able to run an AI task and you can check the AppSheet automation monitoring app or your audit logs to investigate the cause - possible reasons include:
- Bad configuration of the AI task, especially if you give conflicting information in the additional instructions
- Your organization used more than its monthly quota of credits
- Your app ran too many AI tasks in a short amount of time - AppSheet limits the number of Gemini calls an app can make per minute to ensure fairness and reduce spikes in resource use and availability
