The platform
Three layers between
your data and a decision.
Meridex is built around three architectural choices that separate it from both legacy GIS suites and modern mapping canvases.
Data → Skill → Agent — one flow from raw spatial data to a decision
Data layer
Data layer
Connect APIs, MCP servers, files, IoT feeds, and existing GIS sources. Meridex infers schema, stores it in a PostGIS-backed pipeline, and keeps it live — streaming, not just uploaded.
Skill layer
Skill layer
Curated domain knowledge per workflow type — components, defaults, KPIs, anomaly rules, visualization patterns. Skills are the unit of productization: new verticals ship as new skills, not new products.
Agent & interface layer
Agent & interface layer
Describe what you need in natural language; the agent composes the right skills and generates a working application. Refine by conversation. The canvas exists for fine-tuning, not as the primary interface.
The bet
Agent-first
beats canvas-first.
Every incumbent and every modern competitor starts from a canvas: drag widgets, wire data, configure for weeks. It assumes the user is a specialist with time to spend.
Meridex inverts that. You describe the outcome; the agent composes curated skills into a working application and you refine it in conversation. The canvas is still there for fine-tuning — but it’s the fallback, not the front door. That single choice is what makes spatial intelligence accessible to teams without a GIS analyst.
MCP-native
A first-class citizen of the agentic AI ecosystem.
Meridex consumes spatial data via MCP and exposes its own functionality via MCP — so Claude, ChatGPT, and custom agents can query data, generate visualizations, and trigger analyses directly. Meridex is built for where the ecosystem is going, not as a standalone island.
Security & residency
Data sovereignty matters here, and we treat it that way. In-Kingdom data residency is available, the platform is built PDPL-aware from the start, and enterprise SSO is on the roadmap. We engage local legal counsel before any enterprise contract — we’d rather signal awareness than overpromise.