About Koidra
AI in the physical world
The AI wave that rewrote the digital economy has barely touched the factories, plants and greenhouses that consume most of its energy. We build for that half.
The problem
The data these systems run on is in no text corpus
An operator running a dryer, a chiller plant or a glasshouse is not working with documents. They make a control decision, watch how the physical system responds, and adjust the next one. That loop produces the only data describing how their particular plant behaves, and it exists nowhere else. It cannot be absorbed by reading manuals or papers.
This is why a language model, however capable, is not a controller for a live process. It reasons over text rather than over state estimated from sensor streams, it does not model thermodynamics or machinery, and it carries none of the guarantees that writing a setpoint back to a plant requires.
Most of what gets called physical AI is about robots: machines that move through the world with cameras and motors. That is a real problem and it is a different one.
The physical world that consumes the most energy is the one already standing still. Heating and cooling systems, drying and pasteurisation lines, greenhouse climate, chiller plants, thermal processing. They run every hour of every day, they account for a large share of the energy the world uses, and almost all of them are still driven by a person or by rules configured decades ago.
Founder
Kenneth Tran
Dr Kenneth Tran spent his research career at Microsoft Research, building AI systems that learn from interaction with complex physical environments. He led the work on model-based reinforcement learning for operational optimal control, after a class of algorithms that are sample efficient, off policy and transferable. The project named two target applications in 2017: indoor farm control, and data centre energy consumption. Both are Koidra industries today, and the project page is still public.
Sample efficiency is the whole difficulty. A plant will not give you a million episodes to learn from, and it will not let you explore freely, because a wrong action costs hardware or a crop. An algorithm that learns from limited data and carries to a facility it has not seen is the difference between a paper and something an operator will let near their equipment.
Under his leadership the Microsoft team won the first international Autonomous Greenhouse Challenge in 2018, and a Koidra team won it again in 2022.
The other half is a factory. He is a founder of Ayo Biomass, the family wood pellet business in Vietnam, and rebuilt its data and control technology because what it had was obsolete.
That is where the constraints stop being abstract: throughput, equipment behaviour, energy economics, feedstock that varies load to load, and the operational discipline a shift actually runs on. It is also why the biomass pages on this site lead with failure modes rather than benefits.
Koidra is not applying AI to industry from the outside. Research on its own produces papers. Plant experience on its own produces incremental automation. Closing the loop on live equipment needs both, and the combination is rare.
The approach
Three parts, and none of them is a chatbot
Koidra builds control agents for physical systems. They automate the decisions that regulate temperature, humidity, pressure, flow and energy use, minute by minute. The goal is not to replace the equipment already in a facility. It is to give that equipment a better brain.
- A world model of your facility
- A digital twin built from sensor streams, control logs and domain knowledge, describing how this site behaves rather than how a site of this type behaves.
- Model-based reinforcement learning
- Control strategies are evaluated over time rather than optimised one step ahead, so a move that looks good this minute is rejected when it costs more over the next four hours.
- First-principles physics
- Energy balance, mass balance, heat transfer, fluid dynamics and equipment limits are built in, so the agent cannot propose something the plant cannot do.
The method is covered by US patent 12,197,176, granted in January 2025, for simulation and automated control of physical systems using physics-informed deep learning.
See Koidra on your own plant data
Bring a week of readings from one line. We will show you what the platform sees, what it would have flagged, and what it would have scheduled.
Book a demo