SOSX®: System-of-Systems for X is our platform for AI-enabled systems thinking: the definition, research and analysis of problems that are really whole ecosystems of interacting systems, with their feedback loops and emergent properties, in any sector.
Take a broad question such as "what is the impact of hydrogen as a fuel source on the future design of aircraft?". A question like that is really dozens of coupled questions, from fuel-tank sizing to airport storage to mineral supply risk. Nobody can hold all of it in their head, and the answer to one part changes the answer to the others. That is a systems-thinking problem, and doing it properly by hand is slow work.
It supports the decision. The human stays in the chair.
What SOSX does with a broad question
SOSX works as a five-phase pipeline (Scope, Research, Parameterise, Analyse, Report) run by thirteen specialised AI agents.
- It takes the broad question and breaks it into component questions
- AI research agents search the academic and grey literature on each one and identify the systems, actors and influences involved
- It connects them into a typed, directed network and finds the feedback loops
- It attaches parameters (financial, labour, time, materials), each with its source and a confidence
- It optimises over the network, using Bayesian optimisation with sensitivity analysis and Monte Carlo uncertainty quantification
The result is a network you can compute over. Results export into nine MBSE tools and formats. It is in live trials with a large global aerospace manufacturer.
What it is for
SOSX is for management decision-making based on rigorous systems analysis. It supports the decision. The human stays in the chair.
SOSX is not there to make the call. It is there so that the person making the call has done the reading, can see the loops, and knows which assumptions the answer rests on. Because every parameter keeps its source and its confidence, a number in the analysis can be traced back and challenged.
Any sector
The X stands for whatever the problem is about. The hydrogen question is an example, not a limit: healthcare ecosystems, energy grids and supply chains are systems of systems too, and the same method applies to them.
An open question
The networks SOSX builds from research are never complete. There is always another system that could have been included. On 2 October we are putting that problem to UK mathematical scientists at a KE Hub triage workshop: which candidate nodes are most valuable to add, and how much adding them might change the answer. The details are on our events page.
More on the platform is on the SOSX product page. If you have a question too tangled to model by hand, get in touch.
