Loading
Loading
On any customer profile, click Generate suggestions and the AI reads that customer's real service history plus your active catalog, then proposes one to three services worth pitching next — ranked, each with a short reason and a ready-to-edit SMS pitch line that includes their first name. The model does the selecting and ranking; the code keeps it honest by only allowing services that exist in your catalog (it drops any the model invents) and capping the list at three.

Next-service ideas: Suggests the next one to three services to offer a customer.
It's advisory: each suggestion has a Send SMS button that opens the messages composer prefilled with the pitch, and a Build quote button that opens a new quote with the customer and service prefilled. You decide which to act on, edit the wording, and send. If no AI key is set, a deterministic catalog-gap heuristic fills in instead, so the button always returns something usable.
01
When you click Generate, a server query assembles the real picture for that customer — their most recent vehicle on file and their last several appointments with service names, categories, dates, and statuses — alongside your active service catalog with prices. That bundle goes to the fast AI model, which selects and ranks one to three services to pitch next and writes each one's reason and a short SMS pitch. The selection is the model's; the code's job is to constrain it. Any suggestion whose service id isn't actually in your catalog is dropped before it reaches you, and the list is hard-capped at three. So the recommendation is genuinely AI-ranked, and any pick tied to a catalog id is a service you really offer.

02
Each suggestion is a card, not an action queue. A Send SMS button opens the messages composer for that customer with the pitch already typed in, so you can edit it and send from the conversation you'd use anyway. A Build quote button — shown when the suggestion maps to a real catalog service — opens a new quote with that customer and service prefilled, so you can turn the pitch into a priced quote in one step. Neither fires on its own: the AI proposes and prefills, and you are the one who actually sends the text or builds the quote. A small live/stub indicator shows whether the AI wrote the run or the deterministic fallback did.

The complete list. The plan tag above shows which plans include it.
Every meaningful view, the path through it, and the moments that matter — so you know exactly what you're buying.
Send SMS or Build quote
You send; nothing is automatic.

Playbook-aware, so you don't double-message
It's context only — it doesn't drive the ranking.
Marcus T. · Customer profile
Sample Shop LLCWhat should they book next?
Next nudge in 4dThe Sales Playbook already has 2 nudges queued for Marcus, with the next one going out in 4 days. The badge is a heads-up so you don't fire a duplicate touch — it doesn't drive the ranking and isn't an opt-out.
Queued playbook nudges
Context only — passive, never an opt-out, never drives the suggestions.
Who it's for
What it replaces
On any customer profile, the next-service panel sits collapsed behind a Generate suggestions button so the page stays light. Click it and a server query pulls that customer's vehicle, recent appointment history, and your active catalog — all scoped to your shop.
The history and catalog go to the fast AI model, which selects and ranks one to three services and writes each one's reason and an SMS pitch line. Picks are constrained to your real catalog and capped at three. With no AI key set, a deterministic catalog-gap heuristic fills the same fields instead.
Each card gives you a Send SMS button (composer prefilled with the pitch) and, when a catalog service is matched, a Build quote button (new quote prefilled with the customer and service). You review, edit, and act — nothing goes out until you do.
What this looks like in a shop
Illustrative scenario: a service writer at Sample Shop LLC opens a returning customer who's had window tint done but never ceramic. She clicks Generate suggestions and the panel returns two ranked picks from the shop's own catalog — a ceramic coating with a reason noting the tint-only history, and a maintenance detail — each with a short pitch line that already includes the customer's first name. She taps Send SMS on the ceramic pick, tightens one sentence in the composer, and sends; for the second she taps Build quote to price it out. This is the intended workflow, not a reported result.
Anthropic Claude
Selects and ranks the 1-3 next-service picks and writes each pitch (fast model)
Twilio
Carries the pitch you choose to send through the messages composer
Search by name, plate, or VIN in milliseconds. Every appointment, quote, invoice, warranty, and photo attached to the right record — forever.
On Growth and Pro: up to six scheduled nudges per paid invoice over a year — review, warranty (film services only), cross-sell, maintenance, win-back, anniversary — with reply intent AI-classified and acted on automatically. Only the cross-sell step's pitch line is AI-written per customer; the other five are editable template copy.
Build a quote from real line items — services, film, parts, fees — send it, and the customer approves with a drawn signature and a card deposit on their phone. No account needed on either side.
Every customer conversation in one inbox. Auto-reminders run 24/7, but when they reply, a human sees it. MMS, templates, merge fields.