Yearly running cost Assuming 9,600 follow-ups a year
By hand $25K / year 960 hours of work
Subscription $1.2K+ / year
This workflow $138 / year Machine usage only; setup, hosting and review are extra. What should the follow-up workflow do? Send approved follow-ups, or also book jobs when customers reply.
Send approved follow-ups Use exported records; send messages and sort replies. $1,224 – 3,720 setup Add live records and booking Also read live records and book slots on request. $2,088 – 6,120 setup
Which field service software do you use?ServiceTitan Housecall Pro Jobber FieldEdge Other Your office approves each follow-up list and offer. It never messages customers without recorded consent, changes prices or discounts, or contacts anyone who asked to stop.
What is included Pick customers with open estimates or maintenance due from your exported records, exclude opt-outs and recent contacts, draft texts and emails for approval, send approved messages, record stop requests and sort replies for your office.
Start with an export of open estimates, maintenance agreements and contact consent from your field service software, your contact rules and approved offers, and past follow-ups with their replies. The connected option reads records directly, offers open slots and books the job when a customer agrees.
How reliable should the follow-ups be? Set targets for contacting the right customers, accurate messages and handling replies and opt-outs.
Standard The right customers and correct messages, with questions and unclear replies passed to your office. Right customers chosen: ≥99% Message facts correct: ≥98% Included Strict A second check of each list and message and more difficult replies in testing. Right customers chosen: ≥100% Message facts correct: ≥99% Setup +$288 – 840 My own targets Agree your own acceptance requirements with the provider. Quote separately
How these standards are measured Test on held-out customer records and past replies, including customers who opted out, were contacted recently, have an open complaint or a job already booked, and replies that are unclear, angry or ask to stop. Measure customer selection, message facts and reply sorting separately. A message to a customer who opted out counts as a failure.
Targets for your selected standard What is checked Target Right customers chosenCustomers chosen who meet your contact rules, with consent recorded, no stop request, no recent contact, no open complaint and no job already booked, divided by all customers chosen. ≥99% Message facts correctMessages whose estimate, equipment, offer and wording match your records and approved offers, divided by all messages. ≥98% Replies sorted correctlyReplies sorted correctly as booking, question, not now or stop, divided by all labelled replies. ≥95% Stop requests honouredStop requests recorded before any further message is sent, divided by all stop requests in the tests, including those written in other words. ≥100%
Follow-ups are messages to your own customers under your contact rules. Your office approves the lists and offers, answers questions and decides on prices.
How quickly should replies be handled? Choose how soon after a customer replies the reply is sorted and any stop request is recorded. Office callback time is separate.
Within 2 minutes Included Within 60 seconds Setup +$144 – 360 Within 30 seconds Setup +$216 – 600
Timing details Time from the reply reaching your texting account or inbox to it being sorted, with a stop recorded or a booking request on the review page, including model calls, queueing and retries. Confirm texting account limits and volumes with your provider.
The target applies to at least 95% of agreed test runs, with 8 in progress at a time.
How much do you want to spend per follow-up? Set the AI processing budget for each customer follow-up.
Up to $0.15 Included Up to $0.08 Setup +$72 – 240 Up to $0.05 Setup +$144 – 480
Cost details Includes model calls, retries and a shared hosting allocation. Text message and email sending charges, field service software plans and your office's time are separate. One follow-up covers the messages and replies for one customer in one campaign.
Reference machine cost: $0.04 – 0.09 per follow-up at 800 follow-ups a month. The selected cap is a target to test, not a replacement for this estimate.
Where do you want it to run? Run it in your cloud or on your own server. Choose whether customer records may go to an approved AI service.
Run it onYour cloud Local environment AI model accessApproved model API Private model only
Data and access details Runs in a cloud account you control, with access controls, message logs and consent records kept there.
Only the fields a message needs, such as first name, service and estimate summary, go to the selected external model. Agree access and retention first.
Give the workflow read access to estimates, agreements and consent records and permission to send approved messages only. Phone numbers and addresses stay in your environment; the model sees only what a message needs. Private model only keeps customer records on your hardware; the workflow still connects to your field service software and texting account.
How do you want to use it? Choose where you want to use it. You can select more than one.
A follow-up review page Approve the day's follow-up list, read the drafts and see replies sorted into booking, question, not now and stop. Included My existing AI agent Ask your agent which estimates are open, who replied and who asked to stop. Setup +$72 – 240 A dedicated agent Use a dedicated agent to work through replies and prepare callbacks for your office. Setup +$144 – 480