Services
We keep the practice small and the scope tight. Every engagement is one specific system that has to work, scoped against your real constraints and owned by your team on day one. The work falls into two lines. Most clients start with one.
Service line 01
For organizations that live on their maps: utilities, insurers, developers, surveyors, and the small firms doing real work on the ground. We build spatial systems that answer a specific question reliably, and we build them on whichever platform you already run.
Ask a question in plain language and get an answer grounded in your own geographic data, with the parcel, the map sheet, or the record it came from attached. The system understands geography first: it resolves to the right place before it reasons about it.
Pull parcels, hazards, zoning, demographics, and the rest of the public spatial record into a single panel keyed to an address. The kind of desktop site study that used to take an afternoon of tab-switching, returned in seconds with every source cited.
Get what a crew records in the field into the hands of the person who decides, the same day, without a nightly batch job in the middle. Capture, validation, and the reporting layer that makes it legible to someone who was not there.
We would rather make your analysts dangerous than make you dependent on us. Paired builds, working sessions, and documentation written for the person who inherits the system. Engagements are designed to end.
Platform: ESRI or open source
We are not here to sell you a new platform. If you run ESRI and ArcGIS, we build inside it and broker your own credentials rather than moving your data. If you run an open-source stack, or you want one, we build there. The point is that the work honors your licensing, sits where your data already lives, and keeps running after we leave.
Service line 02
The unglamorous middle of a small business: the repetitive, attention-eating work that a person does today because nothing else could. We take it off their plate, carefully, with a human at every decision that matters. This line runs as Inish Agents, our automation practice.
Trigger-to-action pipelines that move information between the systems you already run, with a model doing the glue work that used to need a person: reading a freeform email, pulling out what matters, filing it where it belongs.
The category with the clearest payback. Extracting structured data from invoices, intake forms, field notes, and PDFs, then routing it. The before picture is usually somebody retyping the same shape of information for hours.
Ask your handbook, your contracts, your ticket history, or your ten years of files a question and get a cited answer. We build these small and measurable, and we surface disagreement between sources instead of averaging it away.
For teams that want more than a single workflow: a persistent runtime that remembers, runs scheduled jobs, watches an inbox, and coordinates work across channels, with a person at every decision that matters and a kill switch on every part of it.
The automation work has its own home at inishagents.com. If automation is the reason you are here, start there.
For GIS consultancies
A lot of our best work sits behind another firm’s name, and that’s by design. If you run a GIS or engineering consultancy and a client is asking for spatial retrieval, an agent workflow, or an ArcPy modernization you don’t have the bench for this quarter, we plug in as senior implementation capacity, on your paper, at your standard of quality.
Senior GIS+AI implementation by the engagement or the sprint. You own the client relationship; we do the build and hand it back documented well enough that your team can carry it.
Audits, prototypes, and modernization plans delivered under your brand, in your template. Your client never has to know we exist, and we prefer it that way.
How the work runs
Both service lines run the same way. We keep each phase small enough to finish, and we tell you in writing at the end of each one whether it makes sense to continue.
I.
Two conversations and a written summary. We listen for the twenty percent of the work that actually rewards automation, and we name it in writing before anyone builds anything.
II.
A small, time-boxed build against your real data. A working demo, a cost-to-run estimate, and an honest list of what would have to change to make it production-ready.
III.
The system running against your real sources, with monitoring, backups, documentation, and a person on your team trained to operate it day-to-day.
IV.
A runbook, a training session, and a clear line for when something breaks. If you can cancel and the system keeps running, we built it right.
If one of these is the thing that has been sitting on your list, we would like to hear about it. The first conversation is free, and we will tell you honestly if we are not the right fit.