Lessons from real deployments
Articles on low-code, AI agents and running a business, drawing on published research and case studies.
21 results
Article list
AI Agents
CodeKasten: give the agent a branch, keep the merge for people
CodeKasten lets a team build its own internal tools, and pushes the branch–commit–merge model of source control all the way down to the data. What makes it worth analysing is how it answers the question every company using agents faces: how far does an agent's write access go.
AI Agents
Tech brief, 12–18 Oct 2026: AI and the verification problem
No major Mendix or Power Platform release last week. But Siemens, Meta, Grab and the latest Vietnamese market figures all point the same way: the question companies ask is moving from “what can AI do” to “what data does it use, which process does it run in, and how is the result verified”.
Mobino News
Introducing MaiStudio: the AI writes, a person decides
MaiStudio is a desktop application built by Mobino that lets Mendix developers work with an AI agent in one window. It concentrates on three things: seeing the model visually, reviewing the agent's changes, and controlling the runtime through a UI. MaiStudio never writes to the model directly.
Perspective
Will computer science and IT become foundational subjects?
For more than two decades, computer science and information technology have been read as clear vocational degrees. The speed of AI raises another possibility: that they are shifting into foundational subjects, much as applied mathematics already is.
AI Agents
OpenAI Dots and the rules of engagement for enterprise agents
OpenAI has announced dots — always-on agents with their own cloud computer, connected to more than four thousand apps. For a company, the part worth reading is not what the agent can do, but the rules setting out when it may act alone, when it must ask, and when it must hand work back to a person.
AI Agents
Claude Sonnet 5.5: the price held, the cost per task fell
Anthropic has released Claude Sonnet 5.5 at the same token price as Sonnet 5, but it spends far fewer tokens per task and generates output more than 30% faster. For a company costing out an AI feature, the number to watch is tokens per task, not the benchmark score.
Mobino News
Mobino changes its company name and introduces a new brand look
Mobino Investment Joint Stock Company has formally changed its name to Mobino Technology Solutions Joint Stock Company. The change affects neither the legal entity, the tax code, the team, nor any contract in force. A new brand look arrives with it, led by an orbit in place of the dot on the “i”.
AI Agents
Jev and System One models: typed decisions instead of text
A new lab has released a model that writes no prose at all, returning typed decisions with calibrated probabilities. The part that matters for enterprises is not speed or price, but software knowing when to ask a human.
Operations
Closed-loop quality in oil and gas: Mendix or Teamcenter Quality
From an audit finding to a closed loop of corrective action, training and verification: build it all on Mendix, or put Teamcenter Quality at the core with Mendix around it? A comparison by architecture, data and lifecycle cost.