Ray Poynter, 24 July 2025 ChatGPT’s new Agent Mode is another major leap forward in how AI is advancing, especially in the field of Agentic computing. It also represents a significantly increased risk level. In this post, I outline what Agent Mode is, the associated risks, and provide a simple example. Overview ChatGPT’s Agent Mode… Read More »ChatGPT’s Agent Mode is another Leap Forward – with risks
Ray Poynter, 21 July 2025 Agents are one of the key AI developments that is re-shaping the way we conduct business and processes. An agent is a software tool capable of tackling a task without user supervision. In this post, I will illustrate agents with an example that takes data (for example, from a quantitative… Read More »Creating a Data Checking Agent
Ray Poynter, 22 July 2025 This is another post looking at the hot topic of Agents, building on the post from yesterday that created a Data Checking Agent. Today, I am looking at the combination of Instructions and Knowledge to create a more powerful Agent. Specifically, I will upload an Online Consumer Questionnaire House Style… Read More »Creating an Agent to Check or Create Questionnaires
Ray Poynter, 19 July 2025 In today’s Tip, I’ll show you how to upload a data file to Claude and instantly create an interactive dashboard from your data. The Data and Kaggle.com The data I will use for this demo comes from Kaggle.com. It includes just over 40,000 rows of reviews of Disney Parks, covering… Read More »Create an Instant ‘Data Dashboard’ in Claude
17 July 2025 NewMR recently had the pleasure of hosting Liubov Ruchinskaya, Head of Strategy Analytics and Consumer Planning at Diageo Northern Europe, for a deep dive into the evolving world of insights. With over 22 years in the industry, including extensive experience on both the agency and client sides, Liubov shared invaluable perspectives on… Read More »Unlocking the Future of Insights: A Must-Listen Interview with Liubov Ruchinskaya
Ray Poynter, 29 June 2025 After more than 40 years in the research and insights world, I thought I had fine-tuned my approach to finding the story in the data. Indeed, I have been teaching courses on story finding for over 20 years. However, the rise of Generative AI has caused me to redesign my… Read More »How AI Has Transformed My Story-Finding Method
Ray Poynter, 28 June 2025 With Noriko Kishida (Japan), Tomoko Yoshida (Japan), Dangjaithawin (Orm) Anantachai (Thailand), and Seyo Adeoye (Nigeria), we have created a discussion and note relating to an experiment we ran earlier this year, examining the interaction between the use of ChatGPT and the languages used. You can read the complete note by… Read More »Exploring the Interaction of Language and ChatGPT
Ray Poynter, 19 June 2025 The statistical trap hiding in synthetic respondentsDiscussions about synthetic data are everywhere. Talking about bolstering hard-to-reach quotas, creating digital twins and replacing whole sections of fieldwork. By design, these records replicate the distributions of your original survey, meaning every synthetic element looks plausible. The problem is that this process duplicates… Read More »Synthetic Data and Significance Tests: Why t-tests are Inappropriate and What to Do Instead
Ray Poynter, 6 June 2025 Are you using Notebook LM yet? If not, I think you should be using it; it is frankly quite mind-blowing. To illustrate the power of Notebook LM I took the YouTube link for my presentation “How should you plan for AI and its impact on you?” from the April NewMR… Read More »How should you plan for AI and its impact on you? A Ray Poynter presentation shared via Notebook LM
Ray Poynter, 5 June 2025 Earlier this week, I discussed the use of Digital Twins in research; you can read that post here. Today, I am sharing a concept piece that illustrates one approach to Digital Twins, using ChatGPT. This is an approach I have found helpful with focus group transcripts, but in this concept… Read More »A Digital Twin of Nick Carraway, from The Great Gatsby