Bring your own AI
Ask it anything.
Tell it to do anything.
Plug the AI your team already uses straight into your business — Claude, ChatGPT, Copilot, an agent you wrote yourself. Not a chatbot bolted on the side that can answer a few questions. The real thing, holding the same handles your people hold.
From the van: “what’s my next job?” · “raise a PO to Ferguson for this one” · “mark me arrived and start the checklist.”
From the board room: “which zone is carrying the week?” · “what did callbacks cost us last month?” · “push every PM in Houston out four days and tell me what that breaks.”
Same system, same permissions, same audit trail. A phone at a rooftop unit and a laptop at a board table are two ends of one conversation.
And you do not have to run your company on us to get this. Sync your jobs in from the system you already have, run a few workflows and a handful of events, and your AI can already answer for the work and act on it. The rest of the modules are there when you want them.
Run the company from the driver’s seat
Connect Claude, ChatGPT, Copilot or your own agent once, and the drive between job sites becomes time you can spend running the company. Ask out loud how the week is going, then tell it what to do next, in plain words, and it works in the same records your people do.
Ask about the business
- “How much did we bill this week, and who’s past thirty days?”
- “Which of today’s bank stops still have no proof?”
- “How did plumbing do against HVAC last month?”
- “What does overtime look like so far this week?”
- “What do we owe our vendors by Friday?”
Tell it to do the work
- “Add Hartman Dental as a customer and book a drain cleaning for Thursday morning.”
- “Re-plan Dana’s route around the pickup that just came in.”
- “Set up a crew for the Lancaster zone and put Ivan on it.”
- “Skip the Main Street stop on Friday’s bank round, just this once.”
- “Release this week’s vendor checks.”
What happens when you say it
Your assistant works through the same capabilities your people use on the screen, and it works as you, never as a robot account. It can do anything you could do in ServiceProof and nothing more, it confirms anything that can’t be undone before it acts, and every call it makes goes on the record under your name. A step you have locked behind one of your SOPs stays locked for it, exactly as it does for the screen and the API.
The more you run here, the more it can do
It can answer for your jobs from the day you sync them in, and every piece of the company you move onto ServiceProof after that is another piece you can run by talking. Once payables live here, releasing this week’s checks is one sentence instead of a login to another system.
The pay run behind “release this week’s vendor checks,” by supplier, with every PO number in view.
One capability, every door
Most products bolt an assistant onto the side and give it a dozen things it is allowed to touch. The gap between what the chat box can do and what the app can do is where the disappointment lives.
Here there is no gap, because there is no bolt-on. A capability is written once, and the screen, the API and the agent are three renderings of it.
They are grouped the way the business is: 41 for workflows, 39 for billing, 29 for pricing, 28 for agreements, 23 for parts, 22 for storage, 21 for tax, 20 for the ledger, 19 for rates, 18 each for baselines, integrations and purchasing, 17 for fuel surcharges, 16 for custom fields, 14 each for dispatch, routes and Good Catch, 13 each for payables, tracking and customer messages, and 11 for booking — 76 areas in all.
And the doors are open to you, not just to your AI. The same documented routes are how your data comes out, whenever you want it, and there is no term to serve. The open promise →
How an owner asks
An owner does not want a dashboard somebody built last year for a question they are not asking today. They want to ask the question.
“Which zone actually made money last month?”
A zone is a profit center with its own team and its own timezone, so this is a real question with a real answer — not an allocation somebody invented in a spreadsheet.
“What is late, and who is it late for?”
Late is measured against what was promised, not against when the office got around to it. The answer names customers, not counts.
“How many PMs are we going to miss this month?”
Every obligation carries a window and the room left on it. The system knows which ones can still move and which are about to breach.
“Where is the estimating queue backing up?”
A queue is a column with a person’s name on it. Work sitting in one is measurable, and so is how long it has been sitting.
The point is not the chat box. It is that the answer is assembled from the same records the work is done in, by an agent holding the same read capabilities your reporting does — so there is no second version of the truth to reconcile.
How a dispatcher asks
Seven in the morning, three people calling, and a board with two hundred cards on it. This is the case the tool surface was built for.
-
“Who has not started yet?”
Every visit carries travel, arrival and work-start as separate stamps, so “on the way”, “standing at a locked gate” and “working” are three different answers instead of one status.
-
“Move everything Marcus has left to Dani.”
Each one is a real transfer, one at a time, so each one raises its event and starts the destination queue’s checklist. A bulk update would move the cards and silently start nothing.
-
“A heat wave landed. Push this week’s PMs.”
It shows what that would breach before it does it. PM work is the schedule’s shock absorber and the system knows how far each one may move.
-
“Build tomorrow’s routes.”
One plan per driver, stops in driving order, per-leg drive times. On the board or in a sentence — same capability either way.
-
“Why did job 40219 go to Parts?”
Because step 3 of a published procedure said so, on Tuesday, run by a named technician. The causation is recorded when it happens, which is the only time it can be.
The same actions, written in a dispatcher’s words. What the copilot reaches, a person can still reach by hand.
The copilot on every screen In build
Next, the same assistant moves inside the product. Not a panel per page, but one conversation written into the layout itself — on the board, in the customer record, in the estimator, inside a running procedure — so a dispatcher who asks about a job and then opens a customer does not lose the thread. The rules it will run under are the ones the assistant you connect today already follows.
It will know where you are looking
“Close this job” is meaningless without it, so the copilot will be told which record is on screen.
⚠ That context will be recorded, never trusted. Anything a caller can assert is something a caller can forge, so it rides the audit trail and never the permission check.
It runs as you, not as a robot account
Your roles, your company, your limits. It cannot reach a capability you could not reach yourself, and every act it takes is signed with your name.
A lock is a guide, not a wall
When a procedure gates a capability, the refusal names the procedure that unlocks it, so the assistant does not just refuse. It says “that is locked behind New Commercial Customer — shall I start it?” A system with no way through gets its locks switched off within a month.
The board an agent is talking about. Same lanes, same queues, same cards — it is not a separate reporting copy.
What it will not do
An agent with 734 tools and no rules is not a feature, it is an incident waiting for a Tuesday. Four lines, and they are not negotiable.
It runs the work. It does not author your SOPs.
A procedure written casually in a chat window has no provenance a year later — and provenance is the entire point of writing it down. Authoring stays in the builder, where a version is published, attributed and pinned.
Irreversible acts need authority
Every irreversible capability declares the role it needs, and without that role the call is refused, whoever or whatever makes it. Next, a person who holds the role will be able to approve that single act for someone who does not, with a code — one code, one delete — so you can stop handing out permanent destructive access to five people. In build
The confirmation is the real one
Every irreversible capability carries its own warning, written on purpose, and the agent is handed it with an instruction to confirm with a person before it acts. “This permanently removes the commitment and every covered site, cadence rule and billing line on it.” It is not allowed to be cleverer than a prompt somebody wrote on purpose.
Everything it does is on the record
Which door a call came through is audited on every single write — screen, API, or agent. You can always answer “did a person do this?”
Scale the crew you already have
Every growing field service company knows the pattern. Each new account brings more visits to schedule, more routes to plan, more invoices to send and more payments to match, and the overhead climbs right along with the revenue. ServiceProof is built to break that link, with SOPs, with field workflows, and ultimately with agents.
With SOPs
The office work that used to live in somebody’s memory is written down once and published, so every hand-off starts the next team’s checklist and nothing waits on a phone call.
With field workflows
Every job runs the same procedure whoever is on it, and comes back with its photos, readings and signatures attached, so the proof is in hand before anybody has to ask for it.
And ultimately, with agents
Moving visits, planning routes, sending invoices and recording payments are things an agent can already do for you when you ask, and that is only where it starts.
That is how the work grows faster than the overhead. Agents take on more of the office’s routine work every year, always through your SOPs and under the permissions of the person they act for, so the crew you have carries more of the load and the cost of running the company stops climbing with every new account.
And nothing has to be rebuilt to get there. Every capability in the platform already works without a screen, so when an agent takes on a piece of routine work, the door it needs already exists, the SOP that governs that work already applies to it, and every call it makes is on the record under the name of the person it acts for.
What is real today
We would rather tell you where the line is than let you find it.
| Capability | State |
|---|---|
| 734 capabilities, each a REST route and an MCP tool | Shipped |
| Build-time gate that fails if a capability misses a door | Shipped |
| Scoped API keys that can never out-reach their owner | Shipped |
| An agent connected over MCP, doing real work on real data | Shipped |
| Role gating, confirmation prompts, full audit of the calling door | Shipped |
| The copilot surface inside the portal | In build |
| Approval-by-code for irreversible acts | In build |
| Agents running a published procedure end to end, unattended | In build |
The part that is hard is already done, and it is the unglamorous part: every single thing the product can do is reachable without a screen. A copilot on top of that is a surface. A copilot without it is a demo.