We already have a phone system and an answering service. Why this?
Those route calls or take messages. This actually handles them. An answering service writes down “customer called about water heater” at 2 AM; the agent books the 8 AM slot, confirms it on the call, and logs the job — because it knows your services, your prices, and your schedule. Messages create work for the morning. Handled calls don’t.
What happens when the AI makes a mistake?
It will occasionally — anyone answering a thousand calls a month does. Our job is to make mistakes rare, small, and caught. The agent only answers from knowledge you’ve approved, it’s built to say “let me get someone for you” instead of guessing, and anything that moves money or can’t be undone waits for a person to approve it. We review its conversations, especially in the first weeks, and fix issues at the source. We won’t promise perfection. What we commit to is the work: grounding it, limiting it, watching it, and fixing what we find.
This seems expensive.
Compare it to what missed calls already cost. If your average job is worth a few hundred dollars, a handful of missed after-hours calls a month is the fee — and that’s before counting your own time on repetitive phone work. For context on the alternatives: do-it-yourself AI platforms are cheaper but leave all the hard configuration to you, and fully custom builds typically run $50,000 and up. We sit in the middle: a working, managed agent for a fraction of a custom build, priced by how much you actually use it.
Can't we just use an off-the-shelf AI tool ourselves?
You can experiment, and some owners do. What they usually discover is that the chat part is the easy 20%. The hard 80% is phone lines, connecting your calendar and job software, deciding what the agent is allowed to do, teaching it your actual policies, and watching it so it stays right. That’s the service. You’re not paying for AI — you’re paying for AI that knows your business, and for someone doing the configuration and monitoring work that keeps it that way.
Who owns our data? Does it train someone's AI? What happens to it if we leave?
You own it — your customer list, call recordings, documents, and the agent’s configuration are yours. Nothing from your business is ever shared with another client, and the AI providers we build on (Anthropic’s Claude and xAI) state in their commercial terms that customer data is not used to train their models; data held on their systems follows their retention policies. To get a copy of everything we hold, email support and we’ll arrange a secure transfer to the contact on file. On our end, once you’ve cancelled and been sent your data, we delete it from our systems — apart from records we’re legally required to keep, like invoices and tax records. The full picture is on our
Your data page.
What does the agent do when it doesn't know something?
It says so, and hands off. The agent is deliberately built to escalate rather than improvise: unknown question, upset caller, anything outside its approved scope — it takes a message with full context or transfers to your team, your choice. A confident wrong answer is the one thing we design against hardest.
How long until it's live, and what do you need from us?
Typically a few weeks from kickoff, not months. We need a discovery conversation, access to the tools it should connect to (like your calendar or job software), and your sign-off on what it will know and what it’s allowed to do. Then it launches quietly — closely watched — before taking on full volume.
Are we locked into a long contract? What if we want out?
No long lock-in. There’s no minimum term — you cancel by filing a request in your client portal, and cancellation takes effect after 30 days’ notice. Because the service is prepaid and billed a month ahead, any invoice already issued is still owed, and you’re served through the period you’ve paid for. In practice: you file, the notice period runs, open invoices are settled, and you’re done — no early-termination penalty beyond the month you’ve already been billed for. We’d rather earn next year than lock you in.
How does billing work — when am I charged?
Setup and your first month are due when you sign, before we start configuring. After that, invoices go out on the 15th of each month and are due within 15 days. Each invoice covers the coming month, billed in advance — so you’re always a month ahead, and there are never surprise charges after the fact. Your allowance is a hard cap, not an overage meter: we warn you at 75%, 90%, and 100%, and at the cap the agent pauses new work rather than running up a bill. To keep going you can add prepaid credit (it extends the cap and never expires) or move up a plan.
Do you offer refunds?
No — fees are non-refundable. That covers the setup fee, the monthly service fee once a month has begun, and any prepaid usage credit (which stays on your account and applies to future invoices rather than being returned in cash). Because the service is month-to-month with no long-term contract, the most you’re ever exposed to is the month you’ve already been billed for. The one exception is our own billing error — if we charge you something you didn’t owe, we fix it.