Jul 14 2026

OpenRules AI Assistant in the Release 12.1.0

OpenRules Release 12.1.0 introduces the OpenRules AI Assistant — a graphical tool for testing business decision models in plain English and simulating various end-user interaction scenarios.

To illustrate its capabilities, we use the “Loan Selection” decision model, which helps bank customers find the right loan. We present an actual dialogue between a loan applicant and the decision model, explain how to configure the OpenRules AI Assistant, and provide the decision model’s implementation details.

Functionally, the OpenRules AI Assistant is similar to other agentic AI assistants such as ChatGPT Codex or Claude Code, which can also work directly with OpenRules-based decision services. What sets the OpenRules AI Assistant apart is that it works directly with the decision model without requiring any deployment and needs no additional prompting to restrict it to the provided decision model.

Try OpenRules 12.1.0 and experience the power of rule-based and optimization-based decision services seamlessly integrated with the latest AI advances — with no hallucinations.

Jul 13 2026

Business Rules with Probabilities

Real-world business decision models frequently contain both hard rules and soft rules that can be violated when necessary. Representing and maintaining such rules becomes even more challenging when they conflict with each other and new rules need to be added — at which point a traditional rule-based approach begins to break down.

With this in mind, I will present a different approach that allows subject matter experts to express business rules with a certain degree of probability. Traditional DMN-style decision tables can be extended by assigning a low, medium, or high probability to conflicting rules. A decision engine then determines the optimal decision by satisfying the most probable combination of all applicable business rules.

Continue reading →
Apr 13 2026

AI-Friendly Decision Services

LLMs aren’t decision-makers — at least not yet. But they’ve proven to be remarkably effective translators between natural language and domain-specific languages, unlocking access to decision services built on traditional rule engines, optimization solvers, and machine learning tools. Naturally, decision intelligence platforms have followed suit, providing mechanisms to turn decision models into AI-friendly services compatible with leading LLMs like ChatGPT, Claude, and Gemini.

At OpenRules, we set out to make this process as seamless as possible — no coding, no manual configuration. With the latest release 12.0.0, every OpenRules decision service is AI-ready out of the box. Here’s how we got there.

Continue reading →
Apr 5 2026

Agentic Medical Services

DMCommunity.org has posted a new April 2026 Challenge that aims to explore how LLMs orchestrate rule-based decision services. It describes three loosely coupled medical services that an LLM can use to help a physician determine the appropriate therapy for a patient with Acute Sinusitis. Below, I will demonstrate how OpenRules builds these services and automatically makes them AI-ready, enabling a natural, user-friendly dialogue between a physician and an LLM.

Continue reading →
Mar 22 2026

Peter Norvig about LLMs

In December 2009, Peter Norvig—then the 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.” You can find his analysis here with these first 3 conclusions:

  • Overall, the LLMs did very well, producing code that gives the correct answer to every puzzle.
  • I’m beginning to think I should use an LLM as an assistant for all my coding, not just as an experiment like this.
  • This is a huge improvement over just one year ago, when LLMs could not perform anywhere near this level.

Since LLMs entered the mainstream in November 2022, my colleagues at OpenRules and I have been actively experimenting with them. Like Peter, we have observed undeniable improvements. However, like many of our colleagues in the Decision Intelligence community, we remain cautious about using LLMs to make decisions by selecting the best option from a set of alternatives. That said, LLMs can already play an important role by enabling subject matter experts to interact more effectively with decision services built on proven rules-based and optimization techniques.

Our recent results from deploying OpenRules-based decision services as AI agents have been especially impressive. Business users can now interact with these agents in plain English, dynamically exploring additional conditions to arrive at the most appropriate decisions utilizing the same decision services.

Mar 17 2026

New Tools and Skills Shift

Nowadays, we hear a lot about a strong historical parallel between AI transforming software development today and software transforming traditional engineering decades ago. In both cases, a new layer of abstraction shifts professionals away from manual work toward modeling, design, and decision-making. So, I asked Claude.ai about this analogy. Here is the answer:

“The parallel is striking. In both cases, a powerful new tool class arrives, dramatically accelerates the work, raises the complexity ceiling, and shifts the required skills — but doesn’t eliminate the human. The engineer who mastered CAD outcompeted the manual drafter; similarly, the developer who masters AI tools will outcompete one who doesn’t.

The key insight in both eras: the tool handles computation and execution, while the human retains ownership of judgment, architecture, and intent.”

It must be acknowledged that LLMs can produce high-quality summaries of a wide range of related discussions. Rather than adding to the general discussion, I shared a story at LinkedIn that I witnessed firsthand in the 1980s and let the readers draw their own conclusions.

Feb 24 2026

From Solvers to Decision Factories

After reading the new book “The Decision Factory“, I posted an article with this title on LinkedIn. Here is the conclusion: “Moving from pure solvers to ‘decision factories’ reflects a broader trend: traditional optimization solvers are maturing into Decision Optimization components embedded within larger Decision Intelligence platforms. This lays the foundation for building custom decision systems that can keep pace with an ever-changing real world.” Link

Jan 27 2026

LLM Decision Modeling: From 2023 To 2026

In this LinkedIn post, I compared the 2023 and 2026 results of using LLMs to generate decision models from plain English descriptions. Here is the conclusion:

Three years ago, I was cautious about judging newly introduced generative AI capabilities. Today, even these two examples demonstrate that LLMs can be really good at transforming relatively simple business logic, while they struggle with complex, intersecting conditions. Still, the progress is undeniable. Modern LLMs can take a plain English description of a well-specified business function and generate a reasonably good initial decision model complete with glossaries, business rules, and test cases. These models can then be refined using business-friendly graphical interfaces and executed via decision engines to determine optimal or good decisions. We will undoubtedly see such capabilities, with significantly improved quality, integrated into Decision Intelligence platforms sooner than one might expect.

Jan 15 2026

Decision Playground

Decision Playground is now publicly available. Announced on January 15, 2026, this powerful interactive component of the OpenRules Decision Intelligence Platform enables business users to visually experiment with scenarios, compare alternatives, and optimize decisions—without modifying the underlying models. See how Decision Playground helps a subject matter expert choose the best decision (not necessarily the optimal one) when unexpected constraints emerge: Inside/Outside Production. For more information, click here.

Dec 29 2025

Preview: OpenRules Decision Playground with Decision Pool

In 2025, the OpenRules team devoted significant effort to preparing a special New Year’s gift for its customers: a graphical tool that empowers subject matter experts to leverage a single Decision Model to generate, explore, and compare multiple decisions—making it easier to identify the optimal choice for any situation. Our new Decision Playground is now in final testing with beta customers and will be publicly available in early January. Read the preview.

Dec 16 2025

DecisionCAMP 2026

A new 2026 is around the corner. We’ve just published a new website for DecisionCAMP-2026. This is a major annual event devoted to Decision Intelligence Technologies. It is scheduled to take place online from August 26 to 28, 2026. It is organized by the Decision Management Community and will take place concurrently with the Declarative AI 2026 conference. The Registration is FREE. Call for Presentations is open – you may submit your abstract via EasyChair. Contact us if you plan to present and have any questions.

Nov 22 2025

One More Time About Declarativity

Most experts and practitioners had agreed long ago that decision models should be declarative, meaning a user specifies WHAT the decision problem is and provides test cases with the desired outcome, and then the underlying decision engine or system automatically determines HOW to find the solution. Rule Engines and Constraint Solvers were specifically designed to support the declarativity.

Continue reading →
Nov 12 2025

Solutions for Oct-2025 Challenge

DMCommunity has already received five solutions for its Oct-2025 Challenge “Decision with two objectives” which is looking for decision models that help a web designer to select certain features while satisfying budget and value constraints. It is quite a simple problem for most linear or constraint solvers, so it is no wonder that the first 3 solutions utilized different solvers: Seeker, Pymoo, and OPL CPLEX. What makes this problem more interesting is that it involves two conflicting objectives: total value and total cost. Our decision models are supposed to devise a rational way to trade them against each other.

Continue reading →
Oct 15 2025

Finding decisions for complex problems with multiple interdependent sub-problems

After I wrote about “Making Operational Repetitive Decisions Under Uncertainty,” I found several interesting descriptions of how optimization experts, Adam DeJans Jr. and Helmut Simonis, deal with challenging issues arising in dynamic, real-world settings characterized by high levels of uncertainty. In this LinkedIn post, I quoted their thoughts, including concrete problem examples. Link

Sep 30 2025

Making Operational Repetitive Decisions Under Uncertainty

While just completed DecisionCAMP-2025 was dominated by the integrated use of Generative AI (LLMs) and Symbolic AI (Rules, Machine Learning, Optimization), in my closing notes I concentrated on the topic of making repetitive operational decisions in the real-world, frequently uncertain environments. In this article, I elaborated why it is important now and will be more important as the AI hype pushes our decision-making systems to even wider use within real-world business processes. Link

Sep 18 2025

Advanced Rule Learner: Building Decision Models from Examples

Today, four days before the start of DecisionCAMP-2025, we announced the public availability of the Advanced Rules Learner, a Machine Learning (ML) product designed for business users and well-integrated into the OpenRules Decision Intelligence Platform. Now it can generate working decision models based only on a set of problem examples. I will demo the latest capabilities during my presentation at DecisionCAMP on Sep 22 at noon EDT. You may preview my slides ahead of time. Why did we decide to enhance Rule Learner?

Continue reading →
Aug 20 2025

Why Decision Optimization Remains Underutilized

Adam DeJans just posted: “Most people don’t realize how much of the world runs on a math method called Mixed-Integer Linear Programming (MILP). It is how airlines schedule flights, supply chains allocate products, and manufacturers decide what to make.” https://lnkd.in/e_WAHxYc

He is right. Still, despite their proven effectiveness in real-world decision-making systems, optimization solvers—such as Constraint Programming (CP), Linear Programming (LP), and Mixed-Integer Programming (MIP)—remain underutilized by many decision intelligence practitioners. One contributing factor is the perception that these tools require experts like Adam DeJans to apply optimization effectively.

Continue reading →
Jul 18 2025

Business Rules with Regular Expressions

Almost all programming languages support regular expressions. Many search languages allowed simple wildcards, for example “*” to match any sequence of characters, and “?” to match a single character. Non-programmers may use regular expressions in many situations just as well. In particular, business rules may need to define conditions that use regular expressions. Examples of such rules were specified in the DMCommunity July-2025 Challenge. Below is a possible OpenRules solution.

Continue reading →
Jul 18 2025

OpenRules Release 11.0.0 is publicly available

The new release 11.0.0 of the OpenRules Decision Intelligence Platform (http://OpenRules.com) simplifies the installation process, and the standard installation now includes various OpenRules samples and documentation. We also introduced advanced features to Rule Learner, Rule Solver, and Rule DB. The website OpenRules.com has been unified and now includes product-specific sidebars.

May 19 2025

From Low-Code to No-Code to No-Logic?

Low-code/no-code approaches aimed to accelerate development and empower non-developers to create applications. Nowadays, GenAI automates code generation based only on the problem description in plain English. Do these approaches tend to hide and even remove the application logic along with developers? Read more

By jacobfeldman • Posted in Trends
0
Apr 21 2025

Resolving Conflicts among Business Rules

Ron Ross again brought up the question of “Exceptions to Business Rules”. Ron defines an exception to the rules as a foreseen, explicit set of circumstances in which different-than-normal guidance is to be followed. He gave an example: seeing-eye dogs as an (explicit) exception to dogs not being allowed in a hospital. One comment says: “I heard that there are no exceptions to the BRs. I heard that there are only other BRs.”
This discussion is still as important as it was years ago when we, vendors of Business Rules systems, considered it as a more generic problem of Resolving Conflicts among Business Rules.

Continue reading →
Apr 6 2025

Trying to find an optimal decision without an optimization engine

All provided solutions to the DMCommunity April 2025 Challenge “Case Assignment” use an optimization engine. The OpenRules solution utilized Rule Solver. I decided to try to solve this problem using only rules without any optimization engine. In doing that, my solution failed to satisfy all problem requirements. I believe it could be helpful for Business Rules practitioners to analyze (and potentially improve) my implementation described below.

Continue reading →
Apr 4 2025

Assigning Cases to Analysts

DMCommunity.org published the April 2025 Challenge “Case Assignment”. Here is an OpenRules solution. First, we created a pure business decision model that defined all feasible case-analyst assignments. However, to find a solution that minimizes the total overqualification, we need to use an optimization engine. As usual with OpenRules, we prefer not just to solve the challenge but to build a working decision service that works for different datasets and is available from any remote cloud. The implementation based on Rule Solver is described below.

Continue reading →
Mar 27 2025

New book “Business Decision Modeling with OpenRules”

The new book is now available at Amazon: https://lnkd.in/ef-ygpJg. This book is oriented to subject matter experts who want to build operational decision models for their business environments. No programming skills are required. The objective is to help readers learn quickly how to apply the decision modeling approach to building real-world decision models. This book will guide readers through practical examples, starting with simple business problems and moving to complex ones. After learning how to create decision models, readers may also test, debug, modify, and analyze them using freely downloadable OpenRules software and familiar tools such as Microsoft Excel (http://OpenRules.com).

Continue reading →
Mar 10 2025

OpenRules Solution to Feb-2025 Challenge “Mr Bates vs The Post Office”

DMCommunity.org posted the challenge “Mr Bates vs The Post Office”. I applied Rule Solver to demonstrate how to solve this challenge using several decision tables. Link

Then I decided to ask GenAI to produce a solution for this challenge using JavaSolver API. I was a bit surprised that Copilot is quite familiar with JavaSolver It quickly generated for me a Java program for a simple Arithmetic problem similar to this one. Then I gave the text of this Challenge in plain English, and Copilot generated a very good working solution for this challenge as well! Here it is: https://dmcommunity.org/wp-content/uploads/2025/03/challenge2025feb.copilot.pdf

Feb 23 2025

Discovering Rules From Examples

Watch this short Richard Feynman’s video about Discovering Rules of Chess. He used a chess analogy to explain what we are doing in trying to understand nature: “Imagine that the gods are playing some great game like chess. You don’t know the rules of the game, but you are allowed to look at the board at least from time to time from a little corner, perhaps. And from these observations, you try to figure out what the rules of the game are, what are the rules of pieces moving.”

After watching this video, I decided it could be interesting today to refresh several past projects devoted to the Automatic Rules Discovery based on positive and negative examples. I will describe a few projects in which I and/or some of my colleagues were involved.

Continue reading →
Feb 21 2025

OpenRules and SharePoint Integration

OpenRules announced a new Release 10.5.0 that integrates its Decision Intelligence Platform with Microsoft SharePoint. This development came in response to our large corporate customers who already use SharePoint as their major collaboration and document management platform to store, organize, share, and access information securely.

Why is this development important? For two reasons:

  1. OpenRules users can utilize SharePoint to manage their Rule Repositories
  2. SharePoint users can utilize OpenRules as a full-scale Decision Intelligence Platform.

In this post, I will explain both the benefits and how to integrate OpenRules and SharePoint.

Continue reading →
Jan 30 2025

Decision-Making Systems: Continuing Education

It is interesting to look at the latest Decision Intelligence trends from a 10-year-old perspective when GenAI was not even around. “You don’t program a system, you educate it. Rather than coding into the system, you merely provide a large set of training examples,” – wrote Jean-Francois Puget at that time. Reread my 2015’s post “Don’t Program a System, Educate It!“

Jan 14 2025

AI for Decisions: a look from 2017 and today

After listening to the latest talk of Prof. Bob Kowalski on What is AI?, I remembered his talk about logical AI at the joint session of DecisionCAMP and RuleML+RR in 2017 in London. It also reminded my own prediction about “What is the next “killer” application for Decision Management?” at that time. Here is what I wrote about a Decision Reasoner in 2017:

Continue reading →
Jan 4 2025

Futuristic Poetry and ChatGPT

I wondered how an LLM would interpret questions from some famous but hardly meaningful poetry. My first thought was “Could you play a nocturne on the flute of drainpipes?” (“А вы ноктюрн сыграть могли бы на флейте водосточных труб?”). It is from the 1913 futuristic verse by Mayakovsky.

Continue reading →
By jacobfeldman • Posted in Art, LLM
0
Dec 27 2024

Christmas Word Search

DMCommunity.org offered a relatively simple challenge “Christmas Word Search” for holidays. My first inclination was to ask an LLM to solve it. I certainly was impressed that Copilot (or another LLM-based tool) could quickly build a code to find a correct solution. But then I thought: “Can I, a human, do better than LLM preferably without coding?” Below I describe my experiments from this morning.

Continue reading →
Dec 25 2024

Intelligent Perpetually Running Decision Services

Today ResearchGate confirmed that people continue to read my 2019 presentation “Creating Intelligent Perpetually Running Applications with Business Rules” at the BBC conference. I reread its abstract: “In the AI era, many business applications which consider themselves “intelligent” cannot simply execute a complex rules-based transaction and wait for the next one. To become really “intelligent” applications, they should be able to learn from already executed transactions, accept new facts as they become available, and, when necessary, they should make changes in their own execution logic. This presentation describes a practical architecture that supports the creation and continuing development of such intelligent, perpetually running decision-making applications. This proposed architecture utilizes the modern pub/sub tools with continuous data streams and state machines, allowing subject matter experts to define and maintain behavioral and decisioning rules. It’s been demonstrated by using several real-world scenarios.” Then I went through my presentation with a new interest. If you are also interested in long-running decision services you may read about Stateful Loan Approval and watch Demo of a long-running decision service.

Dec 9 2024

Movie Production Scheduler

This year OpenRules was approached by a film production company that wanted to optimize their movie production scheduling process. They wanted us to build a scheduler that receives the following input: multiple scenes, estimated time to prep and film the scenes, shooting locations, day and night shifts, all characters, cast members with their availability and associated costs, production units, and other related information. The objective of the scheduler is to schedule a production process over a certain period subject to time constraints, actor preferences, location availability, union requirements, and various soft and hard constraints. We’ve successfully and quickly developed a working prototype that satisfied major customer’s requirements and produced good schedules for this particular client. Then we expanded this development to a generic Movie Production Scheduler now available for solving similar scheduling problems with more custom constraints and preferences.

Continue reading →
Dec 8 2024

Integrating Rule Engine and Constraint Solver

OpenRules Rule Solver is an open-source tool that adds the power of Constraint and Linear Programming to Business Decision Modeling. It extends OpenRules Decision Manager to support Declarative Decision Modeling and Decision Optimization.

You may look at multiple decision models from Simple Arithmetic Problems to Smart Investments to see how Rule Solver helps define business optimization problems and produce their optimal solutions. One such decision model was created by our intern to ponder the DMCommunlity Challenge “Rental Boats“.

Continue reading →
Nov 23 2024

Glossary and JSON Interface

Being at the heart of any decision model, OpenRules Glossary uses mandatory columns “Variable Name”, “Business Concept”, “Attribute”, and “Type” to define all used decision variables. It also may include many optional columns such as “Description”, “Used As”, and “Default Value” that allow you to effectively control the input and output of the decision model [read more]. The new OpenRules Release 10.4.1 adds new features to the Glossary that allow our customers to build more flexible JSON interfaces for OpenRules Decision Services.

Continue reading →
Nov 8 2024

OpenRules Training/Consulting

In October-November of this year, OpenRules successfully provided Training/Consulting services for different business units of a major US insurance company. Working closely with their business analysts and software developers, we managed to develop and deploy decision services that became working prototypes for the production-level systems. Contact support@openrules.com if you want to quickly put together a pilot of your decisioning system.

Sep 28 2024

New Rule Scheduler

We introduced RuleScheduler on Sep 19, 2024 at DecisionCAMP-2024 as a new OpenRules component for building decision models for Scheduling and Resource Allocation problems. Such problems traditionally considered very complex and they are usually out of reach for most rule engines. Traditionally, these problems require constraint programming tools and the involvement of technical gurus. RuleScheduler intends to allow business analysts to represent and solve these problems without programming by extending traditional user-friendly decision tables. 

Continue reading →