Agents belong in the back office, not just the chat box

Most "AI for vets" right now is a chat box bolted onto a website. It can answer questions. What it can't do is the thing that would actually help a short-staffed clinic: the work. Surface the patients overdue for vaccines. Draft the recall list. Look up a weight-based dose. Find the open slot and book the visit. That work lives inside the PIMS, and an agent can only do it if the PIMS has a real, write-capable API.

Why the closed PIMS blocks this

An agent is only as useful as the tools it can call. If the system of record won't let software write back (create the appointment, record the note, update the record), then the agent is stuck reading. That's the wall most veterinary AI hits today. It's not a model problem. It's an access problem.

What we're building

OpenVPM ships with an agent that operates on the practice's own data through the same open API any developer can use. It works through typed tools (find a client, pull a clinical summary, calculate a dose, find an open slot, book it), and every write is gated for a human to confirm. It's scoped to a single practice and fully inspectable, because it's open source.

• Tools, not guesses: the agent acts on real records or it doesn't act.
• Human-in-the-loop on every write. The clinic stays in control.
• Bring your own model key. Nothing is hidden; the whole thing is auditable.

We think the clinics that win the next decade won't be the ones with the fanciest chatbot. They'll be the ones whose software lets them put the boring, repetitive work on autopilot, safely. That requires an open foundation. So we're building one.