Feature enhancement: Drag and Drop Tasks to Build AI Applications

By Laura Scavo-Shin

April 28, 2022   ·   3 min read

As many Mantium users know, ease of use is always top of mind as we make improvements and updates to the platform. We recently made some great improvements to a feature we refer to as Intelets. With the revised Intelet concept, you gain increased functionality and ease of execution, even when you build AI workflows.

What is an Intelet?

As the complexity of your desired tasks increase, you will find that you need to combine more than one task prompt together and execute it sequentially. With the Intelets feature, Mantium has made this possible: the output of Prompt A can be fed as the input of Prompt B, thus creating an execution pipeline that can handle complex workflows.

Build AI workflows with Intelets

In order to construct an Intelet, you’ll first determine how many steps the text processing task will involve. For instance, if the task involves two processes, you will need to create two prompts. Then, with the Intelets workflow builder, you will just drag and drop those prompts into place.

Use case example

Let’s say a customer visits a business website and opens their chat assistant to send a request. To process the request, the first prompt determines the category of the request, such as “return request” or “change shipping address”. The second prompt then uses the determined category to send an appropriate response, such as a link with a form the customer can fill out and print a return label, or a link to update shipping information.

This connection of two prompt processing tasks makes up this Intelet. In the business example above, the first prompt is a classification task and the second prompt is a completion task. This means that the first process classifies the input within a specific category, and the second process completes a pattern of text based on the category of the first result.

Building complex AI can require fine-tuning

As a way of improving on the few-shot learning approach, fine-tuning a model lets you train a model with more custom data than what can fit into a prompt. This approach helps you save costs while obtaining better responses for any task. With added fine-tuning, you can make business-specific use cases for nearly any task you desire.

Let’s take a look at Intelets in action!

Watch Josh, a senior developer at Mantium, describe the upgrade with an example. He combines two prompts – one for translation and the other for summarization – to make a single, more powerful AI.

Click here to view the sample prototype from the video.

To learn how Mantium can help you build AI driven workflows for your organization, please drop us a note!

Mantium is dedicated to leading innovation so that everyone can quickly build with AI. From AI-driven process automation to stringent safety and compliance settings, our complete platform provides all of the tools necessary to develop and manage robust, responsible AI applications at scale.


Laura Scavo-Shin
Laura Scavo-Shin is a Content Manager at Mantium, where she oversees developing and curating content for marketing campaigns and activities. Laura enjoys writing and educating customers and prospects on AI and bringing Mantium’s offerings to the masses. Laura holds a Master's of Science in Marketing and a Bachelor's of Arts in Communication. In her free time, she loves traveling with her husband to their favorite beaches in Mexico, the islands of Hawaii, and the Caribbean, riding her Peloton, and loving on her dog Stella Wolf.

Enjoy what you're reading?

Subscribe to our blog to keep up on the latest news, releases, thought leadership, and more.