The headlines are still full of updates about new versions of cutting-edge large language models (LLM) like Gemini, GPT or Claude. Parallel to all this core ai progress, there are also many discoveries and work from many other companies on how to leverage these models to innovate, add more value and reduce costs. It's easy to feel overwhelmed and pressured to keep up with all this progress, I can say that happens to me a lot! In this blog post, I include some of the most important concepts and their potential in products and companies to help you stay up to date.
There are some common buzzwords about how companies are achieving the integration of LLM and other GenAI models into their products or processes. These concepts are: indication, adjustment, recovery augmented generation (RAG) and agents. I'm sure you've heard of several or all of these concepts before, but I think sometimes the differences between the concepts are not clear and, most importantly, we are still unaware of the potential they can bring to our companies or products.
In this blog post we will review each of these concepts, with the aim that in the end you understand what they are, how they work, the differences between them and their revolutionary potential for companies or digital products. . There is no better way to understand the potential of a technology than by analyzing its use in specific examples. That's why I'll walk you through these concepts that revolve around a single use case (posting an ad on a marketplace) to illustrate how each of these trending concepts can be leveraged to drive more value and efficiency.
In most marketplaces, users can post ads or products and the platforms provide a standardized posting process. Let's consider the scenario where this process involves several steps:
- “Publish new item“ Button: Indicates the user's intention to include an item in the list and starts the publishing process.
- Information tab– Users are prompted to provide specific details about the item. Let's imagine that in this case the user is asked to…
