MapAI is available now in Australia. Here's what we built, and why.

Today MapAI launches in Australia. It's free to start, and anyone whose work depends on understanding a place can sign up and ask their first question this morning.

MapAI helps professionals turn fragmented spatial evidence into answers they can understand and stand behind. You ask a place-based question in plain English. MapAI finds and combines the relevant data, runs the spatial analysis and shows you the sources, assumptions and steps behind the result.

This article explains what we've launched, who it's for and what you can expect from us over the next few months.

The problem we kept running into

MapAI grew out of about two and a half years of research at the UNSW City Futures Research Centre. The research started with a question that will be familiar to anyone who works in planning, infrastructure, property, environment or policy: why is it still so hard to get a straight, evidence-based answer about a place?

The data exists. Zoning, hazards, demographics, transport, land use, services: most of it is published, and most organisations hold more of it internally. But before anyone can answer a question like "how much residential land sits within 800 metres of these stations?", someone has to find the right datasets, check how current they are, reconcile boundaries and formats, run the analysis, and then do it all again when the data changes.

GIS systems were built to manage and map data, not to make spatial evidence quick to assemble or easy to verify. So teams either queue for scarce GIS capacity, or work around it with evidence they can't fully trace.

Meanwhile, "chat with a map" tools are arriving fast. Many give you a quick answer and hide how they got there. For decisions that affect communities, budgets and infrastructure, that isn't good enough.

What MapAI does

MapAI is a Spatial Evidence Layer. It sits alongside the GIS and data your organisation already has, and it does the repeatable work between the data and the decision:

• Find. Searches connected open data and your own uploaded files for the datasets relevant to your question.

• Understand. Shows where each dataset came from, when it was updated and what it covers.

• Combine. Aligns boundaries, projections and formats, and joins the data.

• Analyse. Runs buffers, intersections, spatial joins, proximity and demographic cross-tabs on a proper spatial engine.

• Review. Keeps the sources, assumptions and steps visible, so you can inspect how the answer was reached.

What MapAI doesn't do is replace your GIS, or the specialists who run it. Interpretation, uncertainty and accountability stay with the professional. MapAI makes the evidence faster to assemble and easier to check.

Who it's for

MapAI Explore, the product launching today, is for domain professionals: planners, transport planners, infrastructure and asset teams, property and development, environment and policy advisers. Your job is to answer a place-based question well enough to make or recommend a decision. You shouldn't need to become a GIS specialist to do it.

GIS experts are very welcome too. The best results come when GIS teams use MapAI alongside domain colleagues, checking methods and shaping how the organisation's questions get answered. In 2027 we'll add MapAI Source and a QGIS companion built specifically for GIS experts. You can register your interest now.

Already at work behind the scenes

MapAI isn't starting from zero. Our engine already provides the geospatial chat and spatial reasoning inside Urban Copilot, Archistar's AI planning product, funded through the Australian Government's Cooperative Research Centres Projects program with UNSW City Futures as research partner. We also hold the commercial rights to the Infrastructure Sequencing Engine, a housing and infrastructure planning tool being developed with UNSW.

And over the past months, planning, infrastructure and advisory teams across state government, local government and the private sector have been testing MapAI on real questions. Their feedback shaped what launches today, and it will keep shaping what comes next.

How to start

• Individuals: sign up at app.mapai.net. It's free to start, with a monthly allowance of credits. When you need more, buy a credit pack. There are no per-seat licences.

• Organisations: request a structured trial. We work with teams on a real workflow, with a baseline, so you can see what changes.

What's next

We're building in public. Over the coming months you'll see shared team workspaces, saved and repeatable workflows, more data layers and the QGIS companion. You'll also see us publish what we learn, including where MapAI falls short. "Trusted" isn't something we get to claim on day one. It's something we earn through reliable data, transparent methods and your scrutiny.

If you work with places for a living, we'd like you to try it, and tell us what you find.

Steve Taitoko is CEO of MapAI.