If you haven’t tried AI yet (such as ChatGPT or Copilot), you really should—it’s absolutely mind-blowing! Introducing AI into databases is next level.

It’s one of the most impressive technologies I’ve ever encountered. For example, I pasted in an email with the prompt “respond to this email,” and the result was almost ready to send. Then I asked it to “write a poem about Josie and Bryce getting married,” and it did! I kept trying different things, and each time, it produced surprisingly good results. While not perfect, the output was consistently impressive.

After seeing what it could do, we had a chat in the DB Gurus office about how we might use AI into our database platform.

Background

For context, we have spent the last 10 years building our own custom cloud database platform. It’s very clever: it allows us create online prototype databases very quickly – new tables, fields, views, imports, exports, notifications, reports, and so on. Most of this setup is through configuration, and we can then extend it to handle nearly anything.

Our AI Integration Plan

To bring AI into the mix, we’ve introduced a new field type called “AI Response” to our database platform. Now, during configuration, we specify which data should be sent to the AI large language model along with a prompt to guide it. After it is configured the system automatically sends the data to AI, and saves the response in the new field.

Example 1: Auto-Reply to Emails

Here’s one way we’ll use it:

• The database checks an email inbox for new messages.
• When it finds one, it automatically adds it to the database.
• It sends the prompt “Reply to this email:” plus the email text to the AI API.
• The API’s response is saved in the new AI Response field.
• When a user opens the record, they’ll see the original email along with a drafted response ready for review and sending.

Example 2: Answering Technical Questions

We’re also using AI  in our databases to help a client who receives lots of technical questions:

• The user enters the client’s question into a “Question” field.
• Our system sends it to AI and stores the response in the “Answer” field.
• The user reviews the response, possibly edits the suggested answer and sends it back to the client. 

Why This Integration Matters

Of course, the AI large language model won’t always get it exactly right. However, even with some editing, the time savings are substantial. More importantly, integrating it directly into the database offers key advantages:

• No need to open an AI app in a separate tab—it happens automatically.
• Copying and pasting is not required.
• All replies and answers are stored and logged.
• You can track all changes for full transparency.
• Everything stays in one central location.

Want to Learn More?

If this sounds interesting and you’d like to explore our cloud database platform or AI  integrations further, get in touch with us. We’d love to show you what’s possible!