Opening — Why this matters now The easiest AI demo in the world is a model producing something plausible. A product description. A support reply. A defect image. A peer-review report. A compliance explanation. A benchmark answer. The output looks competent enough to be shown in a slide deck, which is often where corporate AI strategy goes to enjoy a short but well-lit life. ...
A regional airline or ground-handling team moved from scattered radio, chat, and checklist updates to a human-reviewed AI coordination layer that tracks turnaround state, detects exceptions, drafts delay explanations, and improves passenger communication.
The dashboard says the judge is fine. The document disagrees. Judge is an easy word to trust. It suggests robes, procedure, and someone in the room who is supposed to be less confused than everyone else. In AI evaluation, the word has become dangerously comfortable. Product teams now use LLMs to score summaries, rank chatbot answers, approve RAG outputs, compare model releases, and decide whether another model’s response is “good enough.” The attraction is obvious: human review is expensive, slow, and occasionally insists on context. An LLM judge is fast, scalable, and does not ask why the evaluation rubric was written five minutes before the sprint review. ...
A remote-site mining operator redesigned its safety reporting workflow from manual record chasing into an agent-assisted process that consolidates field evidence, surfaces risks, drafts reports, and preserves human approval for safety-critical decisions.
A car does not care whether an AI answer is impressive. It cares whether the answer arrives before the intersection. That small timing problem is where a large part of today’s agentic AI discussion becomes unserious. We keep asking whether models are smart enough to act. In cyber-physical systems, the more painful question is whether the system around the model can make action repeatable, bounded, and recoverable when the model is late, vague, or simply wrong. ...
A ticket lands in the queue. It looks ordinary: update a parser, answer a business question, patch a workflow, produce a SQL query. The agent opens the files, explores the schema, writes code, runs a few checks, and submits something plausible. The output is polished. The reasoning trace is confident. The dashboard marks the task as completed. ...
A procurement workflow looks boring until an AI agent touches it. Before that moment, the process is usually wrapped in the comforting machinery of enterprise software: approval rules, validation checks, role permissions, exception paths, and enough audit trails to make everyone feel governed. Then someone inserts an agent and asks it to “handle the workflow.” The agent may know the words. It may call the right tools. It may even produce the next step that looks plausible. ...
Bookings are not glamorous. They arrive through email, booking platforms, supplier messages, customer updates, and last-minute changes that somehow always appear after the plan has already been “finalized.” Someone reads them. Someone reconciles them. Someone checks activity availability. Someone checks transport capacity. Someone updates the planning sheet. Someone notices that one family needs pickup from a different location. Someone quietly prevents tomorrow morning from becoming a small logistical circus. ...
A help desk ticket is rarely solved by the first sentence. Someone says, “The report is wrong.” Then comes the real work: wrong where, compared with what, after which data refresh, under which permission level, and whether “wrong” means mathematically false or merely politically inconvenient. The expert does not just hand over an answer. The expert asks questions, reconstructs context, and turns a vague failure into a useful diagnosis. ...
A model can be wrong because it did not think enough. That part is easy to understand. The more annoying failure is when the model already had the answer, kept going, second-guessed itself into a ditch, and then presented the ditch with confidence. This is the special comedy of large reasoning models: sometimes the expensive part is not the intelligence, but the hesitation after the intelligence has already done its job. ...