Contact We engineer AI around the analytical workflow: model structures, data sources, scripts, review gates and the people responsible for the result. Automation should shorten the path to evidence without hiding how the evidence was made.
The planning question
We start with the work as it exists. That may mean helping a modeller assemble a scenario, interrogate large result sets, trace an assumption to its source, or turn a meeting record into decisions and owned actions. Existing tools remain the foundation when they already work.
AI can misread an incomplete instruction or produce a plausible explanation from the wrong data. Consequential changes therefore require explicit permissions, validation and human accept, edit or reject decisions. We design those controls as part of the system, not as an afterthought.
Experience
We have designed assistants that map natural-language requests to model classes, objects, properties and ordered actions. The useful output is not only a changed file; it is a traceable plan that a modeller can inspect, validate and reverse.
Our prototypes connect questions to large, multi-sector time-series outputs and model relationships. They gather the relevant variables, expose bottlenecks and present a reasoned explanation for review by an energy specialist.
We have scoped transcript ingestion, semantic retrieval, action extraction and project-status workflows, alongside orchestration of existing modelling scripts. Provenance, access control, versioning, error handling and rollback remain visible throughout.
How we work
Map the current tools, handoffs, decisions, failure points and access rules.
Prioritise one repeatable burden with a clear reviewer and acceptance test.
Connect the minimum data and tools, with logs, permissions and review gates.
Test against expert judgement, document limits and transfer operational ownership.
What the team receives
Partnerships & consortiums
We are open to partnerships and consortiums with system operators, public bodies, research organisations, infrastructure developers and technology teams.
Discuss AI Engineering Discuss a partnership