Overview

Can you dump raw plant data and documentation into Claude or GPT and expect accurate analysis? No, and not because the models aren't smart enough.

This session breaks the path to industrial AI into three steps: connectivity, contextualization, and cognition. Connectivity is largely solved. Most plants already extract telemetry from equipment through PLCs, SCADA, and historians. Cognition is ready too: frontier models reason carefully over real data rather than inventing numbers.

Context is the bottleneck. Give a model a few hundred tags streaming from mixed PLCs and it will produce trends and correlations, not diagnosis. It has no way to know which tags sit upstream of which, which signals are causes and which are downstream symptoms, or which correlations actually matter for throughput. That knowledge lives in control system configuration, plant documentation, and operators' heads.

We'll cover why manual tag mapping doesn't scale, why documentation is always stale relative to the systems that actually run the plant, and how a hybrid of deterministic code and configuration analysis plus LLM parsing of unstructured documents can build a context layer that stays accurate without manual labor. We'll finish with live examples of agents built on that foundation: root cause analysis, failure prediction, and throughput optimization.

Presented by Benjamin Simon and Leor Fishman, co-founders of Axilon.

Speaker

Benjamin Simon, Co-founder and CEO, Axilon

Benjamin Simon is the co-founder and CEO at Axilon. Previously, he worked in venture capital, most recently as a Venture Partner at Spark Capital. Before that, he was an undergrad at Stanford and Harvard studying computer science and philosophy.

Leor Fishman, Co-founder and CTO, Axilon

Leor Fishman is the co-founder and CTO at Axilon. Prior to Axilon, Leor was a Senior Backend Engineer at Skiff and a Senior Software Engineer at Fractal. He holds a bachelor's in Computer Science from Harvard.

The material presented has not been peer-reviewed. Any opinions are the presenter’s own and do not necessarily represent those of IChemE or the Process Management and Control and Food and Drink Special Interest Groups. The information is given in good faith but without any liability on the part of IChemE.

Time

15:00–16:00 BST.

Software

The presentation will be delivered via Microsoft Teams. We recommend downloading the app from the Microsoft website, rather than using the web portal.