How can an agent understand what the spatial data actually represents?
Coordinates are not enough. The system must preserve place, identity, time, source, uncertainty, and the state of the software doing the work.
Applied research
We investigate what spatial agents need, then apply what we learn to the systems we build.
Spatial grounding
Spatial grounding connects an agent to what an organisation's places, data, rules, and software state actually mean.
The system must preserve that meaning as it chooses tools, runs programs, creates outputs, and checks the work. That is the spatial requirement we bring to the standard agent stack.
Current programme
These are active research questions, not claims that the problems have already been solved.
Coordinates are not enough. The system must preserve place, identity, time, source, uncertainty, and the state of the software doing the work.
We compare complete configurations because the model name alone does not determine how a workflow behaves.
A useful system must recover, ask for review, or stop when the work cannot be trusted.
Insights
Research notes and engineering guides for people building spatial agent systems.
Spatial grounding, context, tools, durable state, and checking.
Read this subjectPractical work on orchestration, software use, migration, and operational limits.
Read this subjectTechnical guides for the environments where spatial work runs.
Read this subjectAxis Spatial Arena
Arena shows which models, tools, prompts, runtimes, and checks were used, what happened, what failed, and what the result still cannot prove.

Start here
Bring us the workflow, system, or research question you need to make concrete.