Articles
-
The Algorithmic Blindfold: When Data Overrules Intuition
Part 4 of the series “The Human Downgrade”) Some weeks back, I was talking to a friend who works as a deputy production manager at a major manufacturing company. He told me about a change management meeting he attended with a specialized consulting firm. The consultants had built dashboards to monitor production, designed to be […] -
Less Harness, More Agent
Mario Zechner, the founder of libGDX, shipped a coding agent with four tools and a system prompt under 200 tokens. Databricks ran an internal benchmark on it and found that simple harnesses like this cut the cost per task by roughly half at equal quality. Shopify used the same agent to make its Liquid templating […] -
The Exception Paralysis: Why Your Team Freezes When AI Fails
(Part 3 of the series “The Human Downgrade”) Some years ago, while working on-site at a client’s facility, I watched an entire software implementation team freeze in their tracks. They had just deployed a new Warehouse Management System (WMS), and almost immediately, a purely physical problem arose: the barcode labels for the storage bins were […] -
ERX: When Your System of Record Becomes a System of Execution
“Vendors sell an ERX vision while delivering foundational or scalable ERP.” That’s the hard truth from Gartner, and on the plant floor the gap between a shiny dashboard and real execution has never been wider. Gartner recently introduced a new category that clarifies this confusion: Enterprise Resource Execution (ERX). It’s the next generation of business […] -
Why AI is Destroying Your Problem-Solving Skills
(Part 2 of the series “The Human Downgrade”) A former colleague of mine called me the other week just to vent (as usual). He left consulting to run supply chain at a manufacturer, and he had been CC’d on an email from a warehouse manager addressed to the production planning team. The subject line read: […] -
When the Model Is Free, the Harness Is the Business
DeepSeek V4 Flash started a token price war, and the market didn’t stop there. OpenAI cut prices on GPT-5.6 Luna by 80 percent, and Meta’s Muse Spark quoted rates that sit at a few cents per million tokens, provided you accept training on your data (like everyone else probably, but at least they wrote it […] -
The Erosion of Expertise: Why AI’s Authority Bias is Making Us Lazy
(Part 1 of the series “The Human Downgrade”) A few months ago, during a live product demo, a client started asking questions to better understand our ERP solution. After I gave my answer, the client challenged it, claiming they read that a specific feature was available and even cited the exact session code. Surprised but […] -
8 GPUs, One Language, 92 Percent Accuracy: An SLM Story
There is a rundown building in Kaitaia, far north of New Zealand, smelling of old cassettes and damp carpet. Inside, eight processors run a specialized speech AI model built specifically for the Maori language. Te Hiku Media is a tribal radio station serving the Muriwhenua tribes, a community voice founded over thirty years ago without […] -
The Human Downgrade
(Series Introduction: The Human Downgrade) Imagine to watch a person present a 40-slide ERP migration strategy to a steering committee. Every recommendation comes from an LLM. When the client pushes back on a single data flow, the consultant froze, because he simply can’t explain the logic behind his own slides. For this, I believe the […] -
What Kimi K3 Proves About the Compute Monopoly
The corporate narrative insists that building frontier intelligence requires a secret algorithm and an astronomical budget. Moonshot AI just proved that this idea is a constructed illusion. A few days ago, Moonshot AI released Kimi K3. They didn’t just launch an API endpoint and ask developers to sign up for a paid subscription. Instead they’ve […] -
The Modular Blueprint: Assembling the Decoupled AI Architecture
Five episodes ago, we started with a simple problem: AI agents crashing production systems because nobody had thought about isolation. This is the final episode. Here is how all the pieces fit together, and why the architecture matters more than any single model you will ever rent. This is the final episode of Pragmatic AI […] -
The Best AI Implementer Is Not a Developer
The market is currently flooded with certified AI experts who know everything about language models and absolutely nothing about your supply chain. The hard truth is that the best person to implement AI in your company isn’t a developer. It’s your current consultant. The AI Expert Bubble Over the past year, a new industry has […]