The News: Infor announced the availability of a new widget designed to improve the efficiency of using generative AI prompts. The Ask ChatGPT widget leverages Infor Business Context (IBC) messages to create customized and contextual prompts that can be used inside workspaces of Infor ERP applications such as CloudSuite Industrial Enterprise (CSIE) and CloudSuite Distribution Enterprise (CSDE). The widget allows for the simple creation of prompts by using more robust and targeted data contained within CSIE or CSDE to generate a prompt that will provide more context-driven responses via the OpenAI ChatGPT endpoints.
Although an Infor representative says that the widget is made to work with Open AI’s ChatGPT APIs only, Infor customers can easily build a similar widget using Infor’s OS App Designer on top of another large language model (LLM) if they desire.
You can read more about the widget at this link, and the press release highlighting this news and the expansion of the Infor Marketplace.
Infor Announces Ask ChatGPT Widget Using OpenAI APIs
Analyst Take: Infor announced the availability of a widget that is designed to leverage the power of information held within Infor’s ERP applications to help users create prompts that return more context-driven responses. Using OpenAI APIs, the Ask ChatGPT widget is designed to improve workflow and efficiency by allowing users to quickly create prompts by leveraging the content in IBC messages to ensure that the prompt is focused on the desired entities and names.
Creating Targeted Prompts to Improve ChatGPT Responses
A key limitation of ChatGPT and other LLM-based generative AI tools is that they rely on mathematical formulas to generate responses, rather than truly understanding the words or context of the request. This can result in significant effort on the part of the user to properly rephrase or reword a prompt so that the generative tool can return a response that is relevant to that user’s query.
From a business perspective, consider a worker seeking information on a specific division of a company. The Ask ChatGPT widget is designed to allow the worker to run a ChatGPT query that specifically uses the data from a selected entity or name held within the ERP application, simply by selecting the desired entity. The widget will then insert that information and generate a prompt using that information.
The key value of the widget is that the prompt generation is handled within the typical workflow, negating the need to switch windows or open additional applications. This allows for an efficient and productive workflow, whether conducting one or many queries.
Integrating ChatGPT Functions Within an App Limits Distractions
Another key value of using a widget to access generative AI functions is that it eliminates the need for a worker to access the standard ChatGPT interfaces while working. Generative AI tools are still somewhat novel, and it is easy to inadvertently go down a rabbit hole entering prompts that are not relevant to a business task, a scenario which can be a slight distraction at best, and a major efficiency killer at worst. By providing generative AI functions via Ask ChatGPT that are tightly integrated withing a typical workflow, organizations can eliminate or reduce the amount of time that is wasted on non-business related ChatGPT activities.
Widgets Will Not Eliminate the Limitations of Any Public LLMs
Although the Ask ChatGPT widget will help users create more context-aware and focused prompts, the main limitation of LLMs remains, namely that the responses are limited to the data and timeframe initially established by the model’s training parameters, data sources, and date range. Hallucinations are still a possibility, and care must be taken to vet any information gleaned via public LLMs.
Disclosure: The Futurum Group is a research and advisory firm that engages or has engaged in research, analysis, and advisory services with many technology companies, including those mentioned in this article. The author does not hold any equity positions with any company mentioned in this article.
Analysis and opinions expressed herein are specific to the analyst individually and data and other information that might have been provided for validation, not those of The Futurum Group as a whole.
Other insights from The Futurum Group:
Study: Generative AI Is Most Helpful to Less-Skilled Contact Center Workers
Generative AI War? ChatGPT Rival Anthropic Gains Allies, Investors
Automation Anywhere Launches Generative AI Tools
Author Information
Keith has over 25 years of experience in research, marketing, and consulting-based fields.
He has authored in-depth reports and market forecast studies covering artificial intelligence, biometrics, data analytics, robotics, high performance computing, and quantum computing, with a specific focus on the use of these technologies within large enterprise organizations and SMBs. He has also established strong working relationships with the international technology vendor community and is a frequent speaker at industry conferences and events.
In his career as a financial and technology journalist he has written for national and trade publications, including BusinessWeek, CNBC.com, Investment Dealers’ Digest, The Red Herring, The Communications of the ACM, and Mobile Computing & Communications, among others.
He is a member of the Association of Independent Information Professionals (AIIP).
Keith holds dual Bachelor of Arts degrees in Magazine Journalism and Sociology from Syracuse University.
