Requirements elicitation, a critical, yet time-consuming and challenging step in product development, often fails to capture the full spectrum of user needs. This may lead to products that fall short of expectations. This paper introduces a novel framework that leverages Large Language Models (LLMs) to automate and enhance the requirements elicitation process. LLMs are used to generate a vast array of simulated users (LLM agents), enabling the exploration of a much broader range of user needs and unforeseen use cases. These agents engage in product experience scenarios, through explaining their actions, observations, and challenges. Subsequent agent interviews and analysis uncover valuable user needs, including latent ones. We validate our framework with three experiments. First, we explore different methodologies for diverse agent generation, discussing their advantages and shortcomings. We measure the diversity of identified user needs and demonstrate that context-aware agent generation leads to greater diversity. Second, we show how our framework effectively mimics empathic lead user interviews, identifying a greater number of latent needs than conventional human interviews. Third, we showcase that LLMs can be used to analyze interviews, capture needs, and classify them as latent or not. Our work highlights the potential of using LLM agents to accelerate early-stage product development, reduce costs, and increase innovation.

The global artificial intelligence market size is expected to grow at a CAGR of 42.2% from 2020 to 2027, as per a report. At SkillUp 2021, Amar Saxena, Associate Professor, IIM-Amritsar, spoke about the changing dynamics of organisations and the necessary skills required to survive in an AI dominated world. Talking about the data science boom, Amar recalled how SAP training used to be the be-all and end-all to land a well-paid job in the past. He then went on to give the audience a layout of the data science ecosystem. He spoke about the demand-side and the changing dynamics.

Building products that use machine learning or artificial intelligence comes with significant challenges. AI-driven products are not deterministic – they make mistakes, and they behave differently in seemingly similar situations, which is something users are not typically comfortable with. They might also make recommendations that a user disagrees with or didn't expect. Not only is this a risk for the user – they might choose to ignore all the AI features as a result – but it could lead to experiences that make the user decide against using the product again. In this article, we explore three major types of ML-driven products and provide five design considerations for ML product managers.

It is an accepted reality of doing business that customers come and go. Loyal customers might stay with you longer than new customers, but sooner or later they will churn. The idea then is to keep on increasing the tenure of each customer with the right customer engagement strategies. It is key to use Machine Learning for understanding your customers and reducing attrition. Churn or attrition rate is the number of customers who have used your products or services in the past but are not going to continue using them in the immediate future.

Today, software-as-a-service (SaaS) companies can choose from several cloud computing providers, dozens of monitoring providers and hundreds of different apps to increase their efficiency and help bring their solutions to market. While great marketing and brand awareness efforts can make it seem like some companies are more favored in the marketplace, sustained customer growth only occurs with a great product experience. This is especially true given that most cloud solutions are available on a freemium basis, which further inspires prospective customers to try before they buy. As a result, SaaS companies are taking advantage of user-collected data to provide customized experiences, intelligent functions and improved product support. These product improvements are easily deployed thanks to APIs and solutions that make use of artificial intelligence (A.I.).