Applied Computing unveils the next generation of Orbital at ADIPEC, built on a world model for energy

• The new Orbital is built on a world model for energy that learns cause and effect across a whole plant, rather than patterns in data.

• Engineers can build their own dashboards by describing what they want, turn recurring work into apps that run themselves, and teach Orbital as they work. It learns from every interaction.

• Each customer’s world model runs and evolves inside their own environment, and their data and models never leave it.

• The launch follows Applied Computing’s $20 million Series A in July 2026, led by KBR with participation from Databricks Ventures.

Abu Dhabi, UAE, 3 November 2026: Applied Computing, the British AI company building AI for energy operators, today unveils the next generation of Orbital at ADIPEC 2026. The new Orbital is rebuilt on a world model for energy, and puts the power to shape it directly in the hands of frontline engineers.

A world model for energy

The first version of Orbital learned patterns in a plant’s data to carry out fixed tasks. The new Orbital is built on a world model that learns cause and effect instead: how mass and heat move through every connected piece of equipment, and what that means for the plant’s output. Because it understands how the plant behaves, rather than memorising patterns, it is no longer tied to a single workflow or task, and it can adapt to whatever an engineer needs.

The world model is built on a knowledge graph of the plant’s physical interactions and improves itself over time. Each customer’s model runs and evolves inside their own environment, and their data and models never leave it.

What’s new in Orbital

Orbital is Applied Computing’s AI for running energy plants at their physical optimum, every day. It connects to a plant’s live and historical data, spots what is going wrong, explains why using the physics of the process, and recommends what to do next. It is already delivering results at some of the world’s largest refineries, and through KBR INSITE® it is in use on ammonia and olefins units.

The new Orbital adds three major capabilities:

• Dashboards built to order. Engineers can describe the dashboard they want, or pick one of Orbital’s suggestions, and Orbital builds it from live plant data.

• Apps that run themselves. Recurring work, such as the 8 am shift report or a heat and mass balance check, becomes an app that Orbital runs automatically.

• Self-learning. Orbital learns from every interaction and from what engineers tell it directly, so it gets smarter the more it is used, and knowledge about the plant stays when people move on.

Together, these changes remove the need for Applied Computing’s researchers to tune and adapt the model inside each customer’s environment. Engineers can now customise and extend Orbital themselves.

Callum Adamson, CEO and co-founder of Applied Computing, said: “Our mission is to get every energy system running at its physical maximum, and the fastest way to do that is to put Orbital in engineers’ hands. Until now, adapting the model to each plant relied on our researchers. That barrier is gone: Orbital now learns for itself and can be fully customised by the engineers who use it every day. We are bringing it to ADIPEC because this is where the industry comes to decide what the next decade of energy looks like.”

Dr. Samyakh Tukra, Chief AI Officer and co-founder of Applied Computing, said: “The first version of Orbital learned the patterns in a plant’s data. What we have built now is a world model. It learns cause and effect, understands how a plant actually behaves, and gets better every day it runs. A plant is always evolving, and so is the work of the engineers who run it, so Orbital cannot stand still either.”

Applied Computing is demonstrating the new Orbital on its stand throughout ADIPEC, from 1st to 5th November, and will host an Orbital demo day on 2nd November.