During the approval activity we sent the approved suggestion to a special engine that indexed the contents through the RAG indexing engine.
Now that our content is indexed, without having to italy phone number list use any programming skills, we can simply drag and drop a Ask Knowledge Base action onto the stage. This is a special action that can query previously indexed content using our Vector data store and OpenAI, combining the two to find the content and generate an appropriate human-like response for the end user:3
There is a lot of logic to this task, but thanks to a Visual Designer this automation is really accessible to anyone with no programming skills with a single drag and drop action. Let's take a look at this in action!
Wow. As we can see, the RAG chatbot is able to understand the human query correctly and respond in a human-like manner. The total Time-To-Market (TTM) of this application was around 2 hours. There was no “coding” involved.
Conclusions
A visual approach to composing AI applications has given a boost to the development of the application, along with the choice to develop a conversational application rather than a traditional UI-based application.
In the near future, Tiledesk plans to extend its capabilities beyond customer service applications to more general business use cases, leveraging LLM technologies to automate repetitive tasks and streamline AI-powered business processes. The goal is to create conversational apps that can perform complex tasks, such as data analysis, reporting, image and document processing, through simple dialogues and without the need for traditional coding or app development.
