AI receptionist for small business: calls, bookings and handoffs
What an AI receptionist does on a real call, the rules that apply, a sample greeting and a pass/fail checklist to launch one safely.
Gorgias agents get a reply drafted with the customer's Shopify order details already in it, ready to check and send.
Gorgias agents spend much of every ticket copying order numbers, tracking links and policy lines into replies. This copilot drafts a suggested reply for each ticket an agent opens, pulling in the linked Shopify order, the customer's history and the macro that fits. Drafts follow your shipping, returns and refund policies, appear as an internal note, and are sent only by your agent.

AI Support Copilot for Gorgias drafts a suggested reply for each Gorgias ticket an agent opens, pulling in the linked Shopify order, the customer's history and the macro that fits. Drafts follow your shipping, returns and refund policies, appear as an internal note, and are sent only by your agent.
For a Shopify brand, support speed shapes repeat purchases, but agents lose time switching between the order, the macro library and the returns policy on every ticket. In peak season, that slows everyone down exactly when volume spikes. After launch, every ticket arrives with a draft that already has the order details and the right policy applied, so agents reply faster and more accurately. The Scope Card lists the Gorgias fields, macros and approval rules before you order, so nothing reaches a customer without your agent.
Each draft pulls in the linked Shopify order and the customer's history. Agents see a reply built on the real order status without opening another tab or searching the store admin.
Drafts follow your shipping, returns and refund policies, loaded as source documents. They start from the Gorgias macro that fits, so customers hear the same policy whoever is working.
Every ticket an agent opens arrives with an internal-note draft ready to review. Routine order questions can be cleared faster, and nothing goes to a customer until an agent sends it.
Your portal lists these the moment you order. Delivery starts the working day after everything is in and your access is checked.
| Option | Delivery time | Price |
|---|---|---|
| Standard | 20–30 working days | $5,900 |
| Express | 15–25 working days | $6,800 |
| Rush | 10–20 working days | $7,650 |
Before you start: Record a month of Gorgias statistics for response time, tickets per agent and one-touch tickets. Note any sales or launches in that window.
These are things to track, not promised results. Outcomes depend on your data, your team and your market.
The build is paid once. Running it costs roughly $50 to $250 a month for AI model usage and hosting in your own accounts, plus your Gorgias and Shopify plans. Sale periods and holiday peaks push usage toward the top of that range.
Usage during testing is billed to your accounts too.
Ask about running costsSeveral stores or brands with different policies, a third connected system, or more than six workflow types need a written Change Quote. Add a note at checkout and we send it to you.
Request a custom versionMonthly maintenance covers monitoring, fixes and change hours for work such as a new returns window, holiday shipping rules or new macros. It starts after the post-launch support period, bills monthly and can be cancelled any month.
$295/mo (5% of the build price a month, includes 2 change hours)
Optional. Starts after the post-launch support period. Cancel any month.
How maintenance works| Do it yourself with a SaaS tool | Hire a custom agency | Upmark Labs | |
|---|---|---|---|
| Price | Helpdesk AI features bill per ticket or resolution | An ecommerce support agency bills monthly | Ours is one fixed price, shown on this page before you buy |
| Order facts | Agents copy them in by hand | Agents look them up per ticket | Ours drafts with the linked Shopify order details |
| Policy checks | Macros apply the same text to every order | Depends on training | Ours checks returns against the order's dates |
| Delivery | Rules are quick; drafts need tuning | Weeks to onboard agents | Ours has a fixed delivery time shown before you buy, with faster options |
It reads the Shopify orders linked to the ticket in Gorgias, which is part of the two-way sync. That gives it items, fulfillment status and tracking without a separate Shopify connection. If you want it to reach data Gorgias does not link, Shopify can be the second connected system instead.
It checks the order date against your returns policy and, if the request falls outside it, says so in the internal note instead of drafting an approval. The agent then decides whether to make an exception. Exceptions above your limits go to the approver you named at intake.
No. It prepares the refund step with the amount and reason for the agent to confirm, within the approval limits you set. The agent clicks through as usual. If you want refunds handled end to end under a policy, AI Refund Workflow is designed for that job.
Yes, and more consistently. The copilot picks the macro that fits the ticket and fills in the order-specific details, so the standard wording stays and the gaps are completed correctly. The internal note names the macro, so agents can still apply it directly if they prefer.
One fixed price covers the whole build and is shown on this page before you buy, with express and rush delivery listed beside it at a set extra cost. All three include the documented mapping, fifty test scenarios across order, returns and product questions, two rounds of changes and a recorded 60-minute handoff.
Yes, with an add-on. The standard build covers one store's policies and macros. The Multi-Brand Setup add-on configures it for several brands, and the Additional Ecommerce Platform Integration connects a further store platform if one is needed. Both are bought alongside the copilot or added later.
Order the Gorgias edition and each ticket an agent opens carries a draft with the Shopify order details, the right macro and your returns policy already applied.

Answers order status, delivery and change requests using live order data.
