Hi, everyone!
If you've been keeping a close eye on the news recently, you might have noticed that AI and Large Language Models (LLMs) such as ChatGPT are making big waves. They're popping up everywhere, becoming integral parts of countless processes and applications, and for a good reason. The potential of AI is immense, and here at Incentro, we're beyond excited to explore it!
In our journey to explore the power of AI, we've brainstormed countless ways to implement it within the Thinkwise platform. We've thought of various use cases, and today, we're excited to showcase one of them.
Introducing TW-GPT, an application that uses the power of AI to take the Software Factory to new heights. This application incorporates a standout feature - the ability to autonomously generate descriptions for different entities within the Software Factory that currently lack descriptions.
Control procedures and tables can sometimes be a mystery to those unfamiliar with them. They're crucial components of our Software Factory, but without descriptions, it can be challenging to understand their purpose or how they fit into the bigger picture. That's where TW-GPT comes in.
Let's take a sneak peek at how TW-GPT works:
Note: You'll notice that the part of generating descriptions is sped up. This is due to the use of the gpt-4 model which sadly, as of right now, is slower in generating output than the gpt-3.5-turbo model.
Control Procedures:
Tables:
And here's a look at the process flow:
Â
Now, you might be wondering, "Why do we need these descriptions? And why automate the process?"
Firstly, having clear, concise descriptions for control procedures and tables will tremendously help new colleagues or developers who are trying to understand the ins and outs of your application. It's like a welcome guide that says, "Hey, here's what you need to know!"
Secondly, by automating this process, we free our developers from the time-consuming task of writing and updating documentation. Instead, they can focus on what they do best - developing innovative solutions! The potential time saved and productivity gained make this feature an absolute game-changer.
Lastly, automated descriptions play a vital role in initiating the peer review process. By offering clear summaries of control procedures and tables right from the start, TW-GPT ensures a shared understanding among reviewers. This facilitates quicker, more constructive feedback, thus making TW-GPT an invaluable tool for streamlining the development cycle.
In conclusion, we believe that the integration of AI, particularly LLMs like ChatGPT, into the platform will significantly enhance the Thinkwise ecosystem. TW-GPT is just the beginning. It's a small taste of what's possible when we combine the power of AI with the versatility of the platform. And the most exciting part? This is just the start. So, stay tuned for more updates as we have a couple more use cases being worked on right now.
Don’t be afraid to share your ideas and thoughts on applying AI in Thinkwise and let's continue to innovate together!Â
This post is generated by ChatGPT