Practice
Spatial systems fail when they're designed from the org chart instead of the territory. We start every engagement in the data (parcels, networks, easements, the field notes nobody digitized) because that's where the real constraints live. A week spent with the actual records saves a quarter spent arguing about requirements.
A retrieval system answering one class of question reliably is worth more than a platform that demos twelve. We scope to the thing that has to work, ship it, watch it run under real load, and only then decide together what earns a second phase.
Records retention, audit trails, procurement rules: these aren't friction to be engineered around. They're the reason the work matters. We design for the auditor as carefully as for the analyst, and we've found the systems come out better for it.
We measure success by how little you need us afterward. Documentation is written for the person who inherits the system, not for the person who bought it. If a retainer is the only thing keeping a system alive, we built the wrong system.
Inish Labs is Dara O’Beirne: eighteen years in GIS, and an instructor teaching AI for GIS at San Francisco State and UC Davis, which is a claim almost nobody else in this field can make. The practice runs on infrastructure we operate ourselves, and the method isn’t theoretical: we’ve built working proofs of it, from parcel-level wildfire scoring to a permit-velocity index, and you can read what they do and don’t do.
A 30-minute conversation first, free, with something working on the screen instead of slides. Then a short paid diagnostic that ends in a written plan you own no matter what you do next. If we build, it’s fixed-fee and delivered in weeks, not quarters. Most clients then keep us on a monthly retainer to run and extend what we built, and that part is a decision you get to make again every month. We quote real numbers in the proposal, once we both understand the shape of the work.
If that sounds like the kind of team you’ve been looking for (or the kind you were promised last time and didn’t get) we’d like to hear about the problem. The first conversation is free and we’ll tell you honestly if we’re not the right fit.