Two Operators Can Think Differently and Meet the Same Goal
Plants judge operators by results within limits. Agents should be judged the same way.
Pieter van SchalkwykTag
62 posts tagged with "mags".

Plants judge operators by results within limits. Agents should be judged the same way.
Pieter van Schalkwyk
I hear this from skeptics a lot, and they are half right. The answer is grounded in cognitive science: the reasoning is real but non-deterministic, and the decision belongs to a deterministic layer.
Pieter van Schalkwyk
Nate Jones's GLM 5.2 video is really about model lock-in Nate B.
Pieter van Schalkwyk
A week or so ago I joined a call with the IT division of a large organization who thought they had figured out its agent strategy. They walked me through it with some pride: AI assistants loaded with skill files written by their subject matter experts, ready to answer questions across the business.
Pieter van Schalkwyk
List the decisions first. Then decide, for each one, how it should be made, who holds the authority and what evidence it needs.
Pieter van Schalkwyk
The draft European rules for artificial intelligence (AI) in medicine manufacturing are blunt about language models. Annex 22 to the European Union (EU) Good Manufacturing Practice (GMP) guidelines, published for consultation in July 2025, says generative AI and large language models "should not be
Pieter van Schalkwyk
Some decisions are negotiations. Almost no multi-agent system is built that way.
Pieter van Schalkwyk
The frontier labs want a regulator to answer for what their models do. In industry, the company that runs the plant answers for what its equipment does, and it builds the guardrails itself.
Pieter van Schalkwyk
McKinsey shows what single AI agents can already do in maintenance. The harder problem starts when several of them work on the same plant.
Pieter van Schalkwyk
Who funds the change and owns the outcome when agentic operations crosses departmental boundaries? Agentic operations can help a business evaluate production, maintenance, energy and workforce decisions together as conditions change. Acting on a shared assessment may require departments to accept di
Pieter van Schalkwyk
During workshop sessions with a large oil and gas company, we discussed how different artificial intelligence (AI) models could be used across operational use cases. Some applications allowed room to experiment with frontier models and change models regularly.
Pieter van Schalkwyk
An OpenAI research agent got past the blocks on Australia's Medicare statistics portal and nobody noticed for months. Calling it a rogue agent misses the point: both sides got the architecture wrong, and industry has known how to bound automation for decades.
Pieter van Schalkwyk
A new book from XMPro CEO Pieter van Schalkwyk. Software-Defined Operations is an architectural pattern that decouples operational decision and coordination logic from applications, automation and infrastructure, so it can be configured, changed and governed through software. 44 pages, free PDF.
Pieter van SchalkwykShare a few details and we'll unlock the resource right away.
XMPro AI
Agentic Operations
Get in touch
Share a few details and our team will reach out to help — or start a conversation with our AI right away.