Andrea De Mauro, PhD
LightNews LightNews
banner
ademauro.com
Andrea De Mauro, PhD
@ademauro.com
760 followers 580 following 19 posts
Data Analytics and AI Exec Advisor and Founder | Book author, published by Pearson, FT, Packt, Apogeo | Professor of AI, Business and Marketing Analytics | Former Exec at Vodafone and P&G | ademauro.com | linkedin.com/in/andread
Posts Replies Media Videos
Pinned
ademauro.com
Andrea De Mauro, PhD @ademauro.com · Nov 17
After 12 months of writing, countless interviews and many sleepless nights, I’m thrilled to announce with my co-author Michele Pacifico that our new book is out! "The Financial Times Guide to Data-Driven Transformation: Maximise Business Value with Data Analytics"
www.amazon.co.uk/Financial-Ti...
Andrea De Mauro and Michele Pacifico, showing their new book on Data and AI, published by Pearson: The Financial Times Guide to Data-Driven Transformation
ademauro.com
RAG is hardly as “simple” as it looks.
In AI Applications Made Easy, I explain why real-world RAG means more than uploading PDFs and pressing a button. It takes structure, context, business understanding. Now live on @manningbooks.bsky.social (discounted today — www.manning.com/dotd?a_aid=d...).
July 15, 2025 at 10:12 AM
ademauro.com
Interested in learning how to build no-code Agents, RAG, and Advanced Prompts? Check out the New MEAP Deal of the Day on April 24: 45% discount on my new book, "Generative AI Made Easy," along with other carefully selected titles! @manningbooks.bsky.social www.manning.com/dotd?a_aid=d...
Deal of the Day
Manning is an independent publisher of computer books, videos, and courses.
www.manning.com
April 24, 2025 at 7:29 AM
ademauro.com
#LearnSora Prompt: "A Labrador dog with a red tie giving a lecture on marketing at LUISS university in Rome”
". Critique: You can see pinus pinaster, the "maritime pine", typical of the Rome area, outside the window. How many tails has the Labrador got?
#OpenAI #Sora
December 22, 2024 at 11:30 AM
ademauro.com
Teach a marketing student how to build an AI model from scratch, and magic will happen! 🪄✨

During my last semester at LUISS University, I witnessed firsthand how capable and creative students can be when they are empowered to merge management, data analytics, and AI into tangible business results.
Andrea De Mauro, teaching his students at LUISS University in Rome.
December 22, 2024 at 9:21 AM
Reposted by Andrea De Mauro, PhD
andytseng.bsky.social
Reading about #OpenScholar takes me back to those long nights in the library during my PhD. How times have changed! #AI like this is revolutionising how researchers access and synthesise literature. Can we even imagine research without AI now? #Research #LiteratureReview #AcademicSky
OpenScholar: The open-source A.I. that’s outperforming GPT-4o in scientific research
OpenScholar, an innovative AI system by Allen Institute for AI and University of Washington, revolutionizes scientific research by processing 45 million papers instantly, offering researchers citation-backed answers and challenging proprietary AI systems.
venturebeat.com
November 24, 2024 at 8:33 AM
Reposted by Andrea De Mauro, PhD
ademauro.com
Exploring the Four Levels of RAG (Retrieval Augmented Generation): From basic fact retrieval to uncovering hidden rationales, this framework shows how LLMs evolve to provide deeper insights. Adapted from Zhao et al., 2024.
📄 Learn more: arxiv.org/abs/2409.14924
#AI #DataAnalytics #GenerativeAI
The image presents a framework titled "The Four Levels of RAG" (Retrieval Augmented Generation), which outlines the progressive stages of LLM (Large Language Model) capabilities in integrating external knowledge repositories for enhanced reasoning. The framework spans from "Basic RAG" to "Advanced RAG," showcasing increasing value and complexity over four levels. Level 1: Explicit Fact Retrieval Basic RAG involves locating specific facts within a repository to provide answers. External facts, represented as "chunks," are processed by an LLM. This level is nearly out-of-the-box and requires minimal customization. It has some positive impact. Level 2: Implicit Fact Identification The second level integrates facts dispersed across multiple chunks within a repository. LLMs piece together connected information (e.g., facts "F1, F2, F3") derived from content "C." This level moves beyond simple retrieval by establishing contextual relationships between facts. Level 3: Explicit Rationale Application Advanced RAG begins here. The LLM applies provided rationale frameworks to integrate dispersed facts and generate answers. External rationales are represented through flowcharts or structured logic diagrams, enabling a deeper layer of reasoning. Level 4: Hidden Rationale Identification The most advanced stage, where LLMs analyze facts in a repository and infer hidden rationales to generate answers. An example involves solving a "24-point game," where basic arithmetic operations (e.g., addition, multiplication) are combined strategically to reach the solution. This level requires highly curated knowledge and customized implementations. The chart visually represents value (vertical axis) versus complexity/time to production (horizontal axis). A gradient indicates increasing impact and customization needs across the levels. An upward arrow shows growing potential value. The framework is adapted from Zhao et al., "Retrieval Augmented Generation (RAG) and Beyond," 2024.
November 17, 2024 at 6:31 PM
ademauro.com
Exploring the Four Levels of RAG (Retrieval Augmented Generation): From basic fact retrieval to uncovering hidden rationales, this framework shows how LLMs evolve to provide deeper insights. Adapted from Zhao et al., 2024.
📄 Learn more: arxiv.org/abs/2409.14924
#AI #DataAnalytics #GenerativeAI
The image presents a framework titled "The Four Levels of RAG" (Retrieval Augmented Generation), which outlines the progressive stages of LLM (Large Language Model) capabilities in integrating external knowledge repositories for enhanced reasoning. The framework spans from "Basic RAG" to "Advanced RAG," showcasing increasing value and complexity over four levels. Level 1: Explicit Fact Retrieval Basic RAG involves locating specific facts within a repository to provide answers. External facts, represented as "chunks," are processed by an LLM. This level is nearly out-of-the-box and requires minimal customization. It has some positive impact. Level 2: Implicit Fact Identification The second level integrates facts dispersed across multiple chunks within a repository. LLMs piece together connected information (e.g., facts "F1, F2, F3") derived from content "C." This level moves beyond simple retrieval by establishing contextual relationships between facts. Level 3: Explicit Rationale Application Advanced RAG begins here. The LLM applies provided rationale frameworks to integrate dispersed facts and generate answers. External rationales are represented through flowcharts or structured logic diagrams, enabling a deeper layer of reasoning. Level 4: Hidden Rationale Identification The most advanced stage, where LLMs analyze facts in a repository and infer hidden rationales to generate answers. An example involves solving a "24-point game," where basic arithmetic operations (e.g., addition, multiplication) are combined strategically to reach the solution. This level requires highly curated knowledge and customized implementations. The chart visually represents value (vertical axis) versus complexity/time to production (horizontal axis). A gradient indicates increasing impact and customization needs across the levels. An upward arrow shows growing potential value. The framework is adapted from Zhao et al., "Retrieval Augmented Generation (RAG) and Beyond," 2024.
November 17, 2024 at 6:31 PM
ademauro.com
After 12 months of writing, countless interviews and many sleepless nights, I’m thrilled to announce with my co-author Michele Pacifico that our new book is out! "The Financial Times Guide to Data-Driven Transformation: Maximise Business Value with Data Analytics"
www.amazon.co.uk/Financial-Ti...
Andrea De Mauro and Michele Pacifico, showing their new book on Data and AI, published by Pearson: The Financial Times Guide to Data-Driven Transformation
November 17, 2024 at 3:57 PM