Agentic Medical Services

Posted on April 4, 2026 by jacobfeldman

This April-2026 Challenge aims to explore how LLMs orchestrate rule-based decision services. It describes three loosely coupled medical services:

  • Determine Medication and Dosing
  • Determine Creatinine Clearance
  • Drug Interaction Rules

Your LLM should use these three services (instead of its own general “knowledge”) to determine a therapy for a patient with Acute Sinusitis. Here is a possible request: “I have a patient diagnosed with Acute Sinusitis. He is 58 years old, weighs 78 kg, and has a creatinine level of 1.85. Keep in mind that he is Penicillin-allergic and takes Coumadin.” Link

Posted in Decision Modeling | Leave a comment

LLM-Solve 2026

Posted on March 31, 2026 by decisionmanagementcommunity

The workshop “LLMs meet Constraint Solving (LLM-Solve)” aims to bring together researchers exploring the intersection of Large Language Models (LLMs) and Constraint Solving (CP, SAT, SMT, MIP, and related paradigms). This workshop provides a platform to discuss recent advances, challenges, and opportunities in combining LLMs and constraint solving.

Posted in Constraint Programming, LLM, Optimization | Leave a comment

AI Mirages

Posted on March 30, 2026 by decisionmanagementcommunity

Derek Bridge wrote today: “You’ve heard about hallucinations. Now hear about mirages. Multimodal models may reason and answer questions about images that are not supplied.” He refers to this article, which states: “In summary, we show that multimodal AI systems can appear to see when they do not, reason about images that were never provided, and achieve high benchmark scores without genuine
visual access.” Link

Posted in Artificial Intelligence | Leave a comment

The Society of Decision Professionals (SDP)

Posted on March 28, 2026 by decisionmanagementcommunity

The Society of Decision Professionals (SDP) is dedicated to the practice of decision analysis and decision quality. SDP is currently the only certifying body for decision professionals. Here is what Warren Powell wrote about it: “This was such a contrast from my decades of attending the Informs meetings, which consist almost exclusively of academics (professors and Ph.D. students) presenting mathematical models and algorithms, all dreaming of real-world applications.
 
SDP consists entirely of business professionals who are directly involved in the process of making decisions within their companies. I spent a career making trips to observe real-world problems in the field. I was immediately struck that I was sitting in a room full of people who actually make decisions rather than just talk about it.” Link

Posted in Decision Making | Leave a comment

AI Agents are Going Beyond Chatbots

Posted on March 27, 2026 by decisionmanagementcommunity

Bart Peetermans posted: “We are rapidly moving past the ‘Chatbot’ phase and into the ‘Autonomous Agent’ phase… LLMs are not Calculators! LLM-based agents are NOT a replacement for optimization. Linear and non-linear scenario analysis go beyond the abilities of an LLM and are much better catered for by true sourcing optimization tools. Use the LLM for the qualitative heavy lifting; let the optimization engines handle the math.” Link

Posted in Agents, Artificial Intelligence, Optimization | Leave a comment

Enterprise AI is moving toward Decision Systems

Posted on March 26, 2026 by decisionmanagementcommunity

Adam DeJans Jr describes how to think about decision systems through the lens of sequential decision problems. “Most operational environments are not one-time optimization problems. They are ongoing processes where decisions must be made repeatedly as the state of the world evolves.

Consider a transportation network. At any given moment, there is a current state of the system: trucks are located in different regions, orders are arriving, drivers have hours-of-service constraints, weather conditions are changing, and new information is constantly entering the system. Any decision we make (dispatching a truck, accepting a load, repositioning inventory) changes that state and affects the options available in the future. From a technical perspective, these systems usually revolve around a few core components.” Link

Continue reading →
Posted in Architecture, Decision Modeling, Decision Optimization, Decision Tracing, Uncertainty | Leave a comment

Bigger Models or Smarter Teams?

Posted on March 25, 2026 by decisionmanagementcommunity


Philippe Kahn posted today at LinkedIn: The focus on creating larger AI models has been prevalent, but what if the key to achieving AGI lies in collaboration among AI systems? It’s clear that relying on a single “God Model” may not be the solution. The future of AI is not about a singular, massive brain, but rather an ecosystem of agents that engage in debate, verification, and correction. Link

Continue reading →
Posted in Agents, Artificial Intelligence, Human Intelligence, Human-Machine Interaction | Leave a comment

Peter Norvig about LLMs

Posted on March 23, 2026 by jacobfeldman

In December 2009, Peter Norvig—then Director of Research at Google—delivered his lecture “The Unreasonable Effectiveness of Data,” at University College Cork. The alternative title was “Billions of Trivial Data Points Can Lead to Understanding.” I was fortunate not only to attend the lecture in person but also to speak with Peter face-to-face afterward.

In December 2025, Peter posted on LinkedIn: “I am now done comparing three LLMs to my own coding on the Advent of Code problems. The LLMs did great! They couldn’t have done it last year.” Read more

Posted in LLM | Leave a comment

New Tools and Skills Shift

Posted on March 16, 2026 by decisionmanagementcommunity

Read the LinkedIn article written by Jacob Feldman

Posted in Digital Transformation, Human-Machine Interaction, Trends | Leave a comment

Meaning-Driven Architecture

Posted on March 12, 2026 by decisionmanagementcommunity

Jack Jansonius published an article, “When Data Doesn’t Know What It Means.”

Many enterprise data systems suffer from a hidden problem: the data no longer “knows” what it means. Over decades, business meaning has been fragmented across processes, rules and technical structures, making systems increasingly opaque and difficult to control.

Meaning-driven architecture offers an alternative. By explicitly modelling goals, decisions and domain concepts, systems become transparent, testable and easier to govern. Instead of hiding logic in process flows or rule sets, decision tables make reasoning explicit—providing a stable semantic foundation for both traditional IT and AI. Link

Continue reading →
Posted in Architecture, Decision Intelligence, Decision Modeling, Knowledge Representation, Semantic Web | Leave a comment