Industry Playbook

The Auto Repair Shop Stack

Boost work-order conversion 41% with AI quoting, automated declined-service follow-up, and a 6-month return-customer reminder engine.

20 min read 5 modules 31 shops deployed

01. The Problem

Three numbers that should keep you up at night.

An independent auto repair shop sits on a goldmine of work it never bills. The work is already approved, the customer already trusts you, the vehicle already needs it. You just never asked the second time. Here is what the data says about three of the most common revenue leaks in the bay.

We pulled deployment data from 31 independent auto repair shops running on Nirvani between Q1 2025 and Q1 2026. The shops range from single-bay weekend operators to 12-bay full-service outfits doing alignments, diagnostics, brake jobs, timing belts, and fluid services. What we found was consistent across every market, every state, every ticket size.

Three leaks. Each one quantifiable. Each one fixable with the modules in this playbook.

35%
of estimate calls fail to schedule. The customer hangs up to "think about it" and never books.
60%
of declined services never return. The multipoint inspection found it. The customer said "not today." Nobody followed up.
28%
of vehicles miss their state inspection or emissions deadline. They book somewhere else when the sticker turns red.

Each of these is a system failure, not a customer failure. Customers don't track their own brake pad thickness. They don't remember which tech recommended the timing belt last visit. They don't flag the registration sticker on the windshield. That work belongs to the shop. If your shop management software (Tekmetric, Shop-Ware, Mitchell1, NAPA TRACS, AutoVitals) is already storing the data, the only missing link is the outreach layer that turns the data into a booked RO.

The five modules in this playbook are how Nirvani-deployed shops close that gap. None of them require a new shop management system, a new POS, or a new database. They sit on top of what you already have and they reach out to the customer at the moment that matters most.

Quick stat
The average independent shop has $78,400 of declined-service revenue sitting in its database from the last 12 months. That number assumes the shop runs a multipoint inspection on every RO and writes the declines into the work order.

02. Outcomes

What shops on the Nirvani stack actually see.

These are deployment-data medians from 31 shops over 90+ days post-launch. Your shop will not see every number on day one. Module 01 (AI quote agent) typically lifts conversion inside week 2. Modules 02 and 05 compound the longest, hitting peak velocity around month 4.

90-Day Deployment Median
The stack moves four numbers that matter.
41%
Work-Order Conversion Lift
18%
Declined-Service Recapture Rate
2.4x
Return-Customer Visit Frequency
6 wk
Payback Period on N1 Subscription

03. The Stack

Five modules. Each one fixes a leak. Each one stacks.

You can deploy any single module first. You can deploy all five in week one. The recommended sequence is the order below: start with the AI quote agent (Module 01) because it stops new leakage immediately. Then bolt on the declined-service follow-up (Module 02), which lights up your existing pipeline of missed revenue. Modules 03, 04, and 05 are the compounders that build a return-customer flywheel.

5 Modules Plug-In to Tekmetric / Shop-Ware / Mitchell1 OBD2 Pull Optional Runs on N1 ($444/mo) or N2 ($1,500/mo)
01
AI Quote-to-Approval Voice Agent
Answer every service call. Quote common jobs. Book the RO directly into the bay schedule.

The number one leak in a service-writer-driven shop is the call that comes in while the writer is standing next to a lift explaining a brake job to another customer. The phone rings. It goes to voicemail. The caller hangs up. The caller calls the next shop on the Google search results. The work goes to your competitor on Main Street.

The AI quote agent answers in under one second. It is trained on your shop's MAP labor pricing, your common labor times for the top 40 jobs (brake pad replacement, oil change, alignment, AC recharge, timing belt, coolant flush, transmission service, battery, alternator, starter, water pump), and your part-ordering rules (OEM vs aftermarket preference, in-stock vs special-order). It quotes a range, books a drop-off slot, and sends the customer a confirmation SMS.

For jobs that require diagnostics (a check-engine light, an OBD2 code pull, anything outside the common-job library) the agent books a diagnostic appointment and tells the customer the diagnostic fee upfront. It never quotes a number it cannot defend.

  • Always-on phone coverage. Inbound calls answered 24/7, even when the lobby is closed.
  • Real labor time lookups. Pulls from Mitchell1 or your shop management system's labor time database.
  • Bay schedule visibility. Books into open slots, respects lift availability and tech-hours load.
  • ASE-certified tech routing. Routes diagnostics to your senior tech, oil changes to the apprentice bay.
  • SMS confirmation. Customer gets a text with date, time, address, and what to bring (registration, prior service records).
Agent
Thanks for calling Maple Street Auto. This is Jamie. What's going on with the vehicle today?
Customer
My brakes are squealing pretty bad when I stop.
Agent
Got it. Squealing brakes are usually a pad wear indicator. What's the year, make and model?
Customer
2018 Honda CR-V.
Agent
Perfect. What's the current mileage?
Customer
About 78,000.
Agent
And do you remember when you last had the brakes serviced, even rotors turned?
Customer
I don't think they've ever been done.
Agent
Okay. Front pads on the 2018 CR-V at 78k typically run between $280 and $360 with our labor and a quality pad. If the rotors need to be turned or replaced, that's an additional $90 to $180 per axle. We can put you on the schedule for tomorrow at 9 AM or Thursday at 2 PM. Either work?
Customer
Tomorrow at 9.
Agent
Booked. I'll text you the confirmation. Please bring your registration. Anything else you'd like us to look at while it's on the lift?

That call took 47 seconds. The agent gave a price range, booked the slot, and prompted for the upsell ("anything else while it's on the lift"). In the deployment data, agents that ask the "anything else" question lift ticket size by an average of $74 per RO.

Conversion lift, this module alone
Shops report a +27 point bump in quote-to-book conversion vs. front-desk-only in the first 30 days of agent deployment. After-hours conversion goes from near zero to 61%.
02
Declined-Service Follow-Up Sequence
When the timing belt, brake pads, or fluid service was declined, the system reaches back out at the right moment.

Every shop runs multipoint inspections. Most shops write the declines into the RO ("customer declined timing belt, advised due at 90k") and then forget about it. The customer leaves. Six months pass. The timing belt actually fails. The customer is on the side of I-95 calling AAA. The shop that recommended the work first does not get the tow-in revenue because nobody followed up.

The declined-service follow-up sequence reads the structured decline data out of your shop management software (Tekmetric, Shop-Ware, Mitchell1, NAPA TRACS, AutoVitals all expose this) and triggers a follow-up cadence at the exact recommended-by date for each service type.

  • Timing belt declined at 90k. SMS at 88k miles, second nudge at 95k, voice call at 100k.
  • Brake pads at 30% (recommend by 6 months). SMS at month 5, voice call at month 7.
  • Coolant flush declined. Reminder at 4-month anniversary of the recommendation.
  • DEF system service declined (diesel). Three-month follow-up with current state-of-fluid warning language.
  • Alignment declined post-tire purchase. SMS at month 2 with "uneven wear pattern" warning.
Agent
(SMS, day 0 of sequence)
Hi Linda, Maple Street Auto. Last visit we noticed your 2018 CR-V's front pads were at 30%. They'll likely need replacement in the next 8 to 12 weeks. Want us to hold a slot? Reply YES or pick a time at maplestreetauto.com/book. Reply STOP to opt out.
Customer
YES
Agent
Great. Front pad replacement on the 2018 CR-V is $280-$360 with quality pads. We have Tuesday at 10 AM or Thursday at 3 PM. Reply 1 for Tuesday, 2 for Thursday.
Customer
2
Agent
Booked Thursday 3 PM. Confirmation coming. We'll text you 24 hours before. Reply HELP for help.

The sequence runs unattended. The customer does not need to call in. The work-order conversation happens entirely over text, which is how 73% of customers under 45 prefer to schedule service. For high-ticket declined work (timing belts, head gaskets, transmission service over $1,200) the system upgrades to a voice call from the AI agent because the spoken word converts higher on larger tickets.

Recapture rate on declined services
Median 18% of declined-service line items convert to a booked RO inside the first 12 weeks of the sequence running. At a shop with $78k of annual declined-service value, that is $14,112 per year of recovered revenue from work that was already in your system.
03
State Inspection / Emissions Reminder System
30-day SMS plus a voice nudge before every customer's annual inspection or emissions deadline.

In states with annual safety inspections (Texas, New York, Pennsylvania, Virginia, Massachusetts, New Hampshire, Maine, North Carolina, Missouri, West Virginia, and others) or annual emissions testing (California, Colorado, parts of Arizona, parts of Illinois, Maryland, the DC area), the inspection deadline is the single most predictable recurring service event. Every car needs one per year. Every customer forgets when theirs is due. Whoever reminds the customer first wins the inspection and any failed-component repair that comes with it.

The reminder system pulls the inspection-due date from the customer's vehicle record (stored on the registration tab in your shop management system or scraped from the sticker date on the prior inspection invoice) and schedules a three-touch sequence ending the week before expiration.

  • 30 days out. SMS: "Your 2018 CR-V is due for state inspection by April 15. Book now."
  • 14 days out. SMS with calendar link and price ($25 inspection, $7 emissions per local statute).
  • 7 days out. AI voice agent calls to book. ~38% conversion on this call.
Agent
Hi, this is Jamie from Maple Street Auto. Just a friendly reminder that your 2018 CR-V's state inspection sticker expires April 15. Would you like to get on the schedule before the deadline?
Customer
Oh wow, I totally forgot. Yeah, what do you have?
Agent
Inspection takes about 30 minutes. I have Monday at 11 AM, Wednesday at 2 PM, or Friday at 9 AM. Which works?
Customer
Wednesday.
Agent
Wednesday at 2 PM is yours. While we have you, any new noises or warning lights since your last visit?
Customer
Now that you mention it, my check engine light came on last week.
Agent
Good catch. We'll run a quick OBD2 code pull during the inspection. If it's a simple sensor we can fix it same-day. If it's bigger, we'll get you a quote before any work starts. Confirmation text coming.

That call surfaced an upsell that would have otherwise gone to whoever ran the inspection. The AI agent is trained to ask the "noises or lights" question on every inspection booking. Average upsell capture rate: +$112 per inspection RO.

Deadline-miss recovery
Shops on this module see inspection-miss rate drop from 28% to 6% within one inspection cycle. The recovered customers stay in-network for the rest of the year because the inspection visit re-anchors the relationship.
04
Maintenance Schedule Engine
By VIN and mileage. Anticipate the next service. Prompt the customer before they shop around.

Every vehicle has an OEM-recommended maintenance schedule. The 2018 Honda CR-V needs an oil change every 7,500 miles, a tire rotation every 7,500 miles, a transmission fluid service at 60k, a spark plug service at 105k, and a timing chain inspection at 120k. The OEM publishes the schedule. Your shop management software (Mitchell1, AutoVitals, NAPA TRACS) has the schedule loaded. The customer has no idea any of it exists.

The maintenance schedule engine takes the customer's VIN, pulls the OEM maintenance schedule, tracks the customer's actual mileage (from the last RO odometer reading plus an average-miles-per-day extrapolation), and surfaces the next due service in the form of a personalized SMS.

  • VIN decode on first visit. Decodes year/make/model/trim/engine/transmission.
  • OEM maintenance schedule mapping. Pulls Honda Maintenance Minder, Toyota Care, Ford recommended service, etc.
  • Mileage extrapolation. Tracks days since last visit + miles delta to estimate current odometer.
  • Personalized SMS. "Your 2018 CR-V is due for a transmission fluid service in the next 1,500 miles."
  • Book-now CTA. One-tap link to the bay schedule, pre-loaded with the recommended service.
Agent
(SMS)
Hi Linda, Maple Street Auto. Based on your 2018 CR-V's mileage, your transmission fluid service is due in the next 1,500 miles. Honda recommends this at 60k to extend transmission life. It's a 90-minute service, $189. Book a slot at maplestreetauto.com/book. Reply STOP to opt out.
Customer
Is that really necessary? My friend said the dealer is just trying to sell me stuff.
Agent
Fair question. The 60k trans service is in Honda's maintenance minder schedule for your specific trim and year. Skipping it doesn't fail the car immediately. It does shorten the life of the transmission, which is the most expensive component on the vehicle to replace ($3,200-$4,500). The $189 service is preventive. Happy to text you the OEM schedule if you'd like to see it.
Customer
Send it. And book me for next Tuesday.

The agent did not pressure. It cited the OEM source. It offered the schedule for the customer to verify. It still got the booking, because the customer trusted the answer. That is how maintenance-schedule outreach should always feel. Pushy gets blocked. Educational gets booked.

Return-customer visit frequency
Shops running this module see return-customer visit frequency rise from 1.4 visits/year (industry baseline) to 3.4 visits/year. That is a 2.4x multiplier on customer lifetime value with zero increase in acquisition spend.
05
Review Acceleration
Post-service SMS to the happy customer. Google review handoff. Negative-feedback intercept.

The single highest-converting moment for a Google review is 90 minutes after the customer picks up the vehicle and drives it. The brakes feel firm. The alignment feels straight. The lights work. The customer is feeling the value. That is the moment to ask. Not three days later. Not at the counter when the customer is in a hurry to leave.

The review acceleration module fires an SMS 90 minutes after the RO is closed in your shop management software. The SMS asks the customer to rate the visit one to five. Four or five stars gets a Google review link. One, two, or three stars gets a private feedback form that routes to the shop owner's inbox before it ever hits Google.

  • 90-minute trigger after RO closed. Tied to your shop management system's "vehicle delivered" event.
  • 5-star rating gate. 4-5 stars route to Google. 1-3 stars route to a private intake form.
  • Pre-filled Google deep link. Opens the Google review form with the shop pre-selected.
  • Owner alert on low ratings. Negative feedback triggers a phone call from the owner within 4 hours.
  • Service-writer attribution. Each review tagged with the writer's name for performance tracking.
Agent
(SMS, 90 min after RO closed)
Hi Linda, hope the CR-V is driving better. On a scale of 1 to 5, how was your visit today with Maple Street Auto? Reply with just a number. Reply STOP to opt out.
Customer
5
Agent
That's wonderful. Would you mind sharing your experience on Google? It takes about 30 seconds and helps other Honda drivers in the area find us. Link: g.page/r/mapleauto. Thank you, Linda.

Compare the 1-star branch:

Customer
2
Agent
I'm sorry the visit didn't meet your expectations. The owner, Mike, would like to make it right. Can you share what happened? Reply here and Mike will personally call you within 4 hours. Your honest feedback won't be shared publicly.

That intercept is the difference between a 2-star Google review tanking your local pack ranking and a personal phone call from the owner that converts the unhappy customer back into a regular. Shops on this module average +1.4 Google reviews per week with a star average that drifts from 4.3 to 4.7 inside the first 90 days.

Star rating impact
A move from 4.3 to 4.7 stars on Google correlates with a +34% lift in Google Business Profile click-to-call volume, according to BrightLocal's 2025 SMB rankings data. More clicks. More calls. More work.

04. Implementation

30 / 60 / 90 day roadmap.

You do not deploy all five modules on day one. You sequence them so each one compounds the next. Module 01 lights up new conversion in week one. Module 02 reaches into your back catalog of declined services. Modules 03, 04, and 05 build the flywheel that turns one-time customers into 2.4x-frequency regulars over the next quarter.

30
Days 1-30: Conversion Layer
  • Deploy AI Quote-to-Approval Agent (Module 01).
  • Connect to Tekmetric / Shop-Ware / Mitchell1 / NAPA TRACS via API.
  • Load top 40 common jobs with MAP labor pricing.
  • Train agent on shop tone, service-writer style, technician routing rules.
  • Go live with after-hours coverage first, then daytime fallback.
  • Track quote-to-book conversion week-over-week.
60
Days 31-60: Recapture Layer
  • Activate Declined-Service Follow-Up (Module 02).
  • Backfill the last 12 months of declined ROs into the sequence.
  • Activate State Inspection / Emissions Reminder (Module 03).
  • Build the 30/14/7-day inspection cadence for every active customer record.
  • Monitor declined-service recapture rate. Target 12%+ by day 60.
  • Tune the cadence pacing based on customer response signals.
90
Days 61-90: Flywheel Layer
  • Deploy Maintenance Schedule Engine (Module 04).
  • VIN decode every customer record. Map OEM schedules.
  • Activate Review Acceleration (Module 05).
  • Connect 90-minute SMS trigger to RO-closed event.
  • Run weekly metric review with shop owner: conversion, recapture, frequency, reviews.
  • Lock in the playbook. The stack runs without daily attention.

Implementation is handled by the Nirvani onboarding team. The shop owner spends roughly 6 to 9 hours total across the 90 days. That includes the initial intake call, the script review for Module 01 (we recommend service-writer voice and tone), and three weekly check-in calls during the first month. After day 30 the stack runs on its own with monthly check-ins for tuning.

The shop does not need to change shop management software. Tekmetric, Shop-Ware, Mitchell1 Manager SE, NAPA TRACS, AutoVitals, Identifix, ALLDATA Manage, and Auto-Repair-Cloud are all supported via API. If your software is not on the list, we offer a manual import workflow that runs on a nightly batch.

05. ROI Snapshot

What the math looks like for a 3-bay independent.

A representative 3-bay shop running 22 ROs per week with a $480 average ticket. Pre-stack baseline. Post-stack at day 90.

Avg Ticket Lift
+$74
Per RO. Driven by upsell prompts and the "anything else while it's on the lift" pattern in Module 01.
Work Orders / Week Delta
+9 ROs
From 22 to 31 ROs per week. Mostly recovered declined services and inspection-deadline catches.
Shop Hours Utilization
+18%
Tech hours go from 64% to 82% utilization. The lift is the lift. No new techs hired.

Pre-stack revenue: 22 ROs/week x $480 x 4.3 weeks = $45,408/month. Post-stack revenue: 31 ROs/week x $554 x 4.3 weeks = $73,838/month. Delta: $28,430/month in incremental revenue. Subscription cost on N1: $444/mo. Payback on the first incremental RO in week 2.

For multi-location operators or shops above $1M annual revenue running multi-channel marketing, the N2 tier at $1,500/mo adds the dedicated voice number cluster, the Yelp / Google Business Profile syndication layer, and the advanced customer-segment routing that lets you treat a fleet customer differently from a retail customer.

Payback period
Median 6 weeks to full payback on N1 across the 31-shop cohort. Fastest payback recorded: 9 days (high-volume tire and brake shop in a college town). Slowest payback: 14 weeks (single-bay specialty European import shop, low call volume by design).

06. Case Study

3-bay independent. 90 days. Numbers.

Composite Profile

Maple Street Auto. Suburban metro market. 3 lifts, 1 alignment rack.

22 yr-old shop / Owner-operator + 2 ASE techs + 1 service writer / 1,400 active customer records

Maple Street Auto (a composite based on three real Nirvani deployments) is the kind of shop that runs on word-of-mouth and Google. Owner Mike has been turning wrenches for 28 years. His service writer Jamie has been there 11 years. They run on Mitchell1 Manager SE. The shop does brake jobs, timing belts, AC work, alignments, state inspections, and the occasional engine swap. Average ticket is $480. Pre-deployment monthly revenue: $45,408.

Mike was losing calls every day. The phone would ring during a customer counter conversation. Jamie would let it go to voicemail. Maybe 1 in 5 voicemails got returned same-day. The rest went to the next shop down the road. Mike knew it was happening but he could not justify hiring a second service writer at $52k/year fully loaded for what felt like a phone-coverage problem.

Mike deployed the Nirvani auto repair stack on a Monday. Day 1 the AI quote agent was answering calls. By day 14 the declined-service follow-up sequence was processing 11 months of backfilled declined ROs. By day 60 the inspection reminder cadence was live. By day 90 the maintenance schedule engine was personalizing outbound SMS to every customer record. Here is what the numbers looked like at day 90.

+44% Work-Order Conversion
$31K Recovered Declined Revenue
4.8 stars Google Avg (was 4.4)

The 44% conversion lift came almost entirely from after-hours and during-counter-conversation calls that previously went to voicemail. The $31,000 in recovered declined revenue came from timing belts (8 ROs at an average of $1,840), brake services (24 ROs at $340), and fluid services (19 ROs at $189). The star rating climb came from 47 net new Google reviews in 90 days, of which 41 were 5-star, 4 were 4-star, and 2 were 3-star (both intercepted by the private feedback form, both turned into regulars after Mike's personal call).

"I should have done this two years ago. The phone agent alone paid for the whole stack inside the first month. The thing that surprised me was Module 02. I had no idea I was sitting on that much declined work just in my Mitchell records. Most of those customers were happy I called. They just forgot." Mike. Owner, composite shop.

Get the full auto repair playbook by SMS and email.

We will send you a 12-page PDF with the deployment-ready scripts for all 5 modules, the Tekmetric / Shop-Ware / Mitchell1 connection guides, the MAP labor pricing template, and a 30-minute strategy slot with the founder if you want one.

On the way.

Check your inbox for the 12-page PDF and your phone for a single confirmation SMS. Sammy will reach out within 24 hours if you flagged the strategy-call option.

Frequently Asked Questions

Does this work with my shop management software?
Yes for all of the common ones. Tekmetric, Shop-Ware, Mitchell1 Manager SE, NAPA TRACS, AutoVitals, Identifix, ALLDATA Manage, and Auto-Repair-Cloud are all supported via direct API integration. The data we read includes the RO header, customer record, vehicle record (VIN, year/make/model/mileage), multipoint inspection results, declined line items, and the RO-closed event.

If you are on a less common system, the manual import workflow runs a nightly CSV batch that handles all five modules with a 24-hour lag instead of real-time. Effectiveness drops by roughly 12 percentage points but the stack still pays for itself.

How does the OBD2 integration work? Do we need a scanner per bay?
OBD2 integration is optional and only relevant for Module 01 (the AI quote agent). When a customer mentions a check-engine light, the agent books a diagnostic appointment and quotes the diagnostic fee upfront. The actual OBD2 code pull happens at the shop on your existing scanner during the appointment. The agent does not need to pull codes itself.

For shops that want code-level pre-qualification on inbound calls, we offer an optional customer-facing OBD2 reader workflow where the agent walks the caller through a free phone app that reads the code over Bluetooth and texts it back to the shop. This is a Tier 2 feature reserved for shops on N2 or higher.

How do parts ordering and OEM vs aftermarket pricing flow through the AI quote?
The agent quotes a labor range based on your MAP (Manufacturer Approved Pricing) labor table and a parts range based on your default parts policy. Most shops set the default to "quality aftermarket with OEM option on request." The agent quotes the aftermarket price as the base and notes that OEM is available at a 22-35% premium. If the customer asks for OEM, the agent re-quotes.

Parts ordering itself happens on your shop's existing parts platform (NAPA, AutoZone Pro, O'Reilly First Call, WorldPac SpeedDial, AAIA Aces, RockAuto for niche cases). The agent does not place the order. It books the appointment and the tech writes the parts order at the start of the RO based on the diagnostic and customer-approved parts type.

Can the AI agent dispatch a technician or move work between bays?
The agent books into open bay slots based on the rules you configure. It does not move work in progress between bays mid-day. If your senior ASE-certified tech is the only one doing diagnostics, the agent will route any "check engine light" booking to that tech's slot. If your apprentice handles oil changes, those go to the apprentice bay.

Mid-day re-routing (when the senior tech finishes early, when the alignment rack frees up, etc.) stays with your service writer. The agent surfaces the open slot, the writer makes the call.

What happens when a customer needs a tow? Can the agent dispatch one?
The agent can hand off to your preferred towing partner via a three-way call or a direct SMS handoff. Shops typically have 1-3 towing partnerships (a local independent, a AAA-affiliated dispatcher, and sometimes a flatbed-specialty operator). The agent collects the customer's location, vehicle, and the nature of the breakdown, then either patches the call to the tow partner or texts the customer the tow partner's direct number with a pre-filled SMS.

The agent does not negotiate tow rates or guarantee tow availability. That stays with the tow operator. The agent's job is to keep the customer's vehicle in your network instead of letting them call a random tow company that delivers to whichever shop pays the kickback.

How is the SMS A2P 10DLC compliance handled? We've had carriers block our texts before.
All SMS sends through Nirvani run on registered A2P 10DLC campaigns with documented opt-in, required STOP / HELP keywords on every initial message, and a customer-facing SMS Privacy and Terms page. Phone numbers captured on the shop's intake forms are never shared with third parties for marketing. Reply STOP and the customer is suppressed from all future SMS. Reply HELP and they get the shop's support contact.

Carrier filtering (the blocks you have experienced before) usually happens because the sender is using an unregistered campaign or shared shortcode. The Nirvani auto repair stack uses dedicated long codes registered to your shop's business identity, which clears the major carrier filters.

What does this cost and is there a contract?
The auto repair stack runs on the Nirvani N1 plan at $444/month for a single location with up to 1,500 active customer records. Multi-location operators, shops above 1,500 active records, or shops that want the multi-channel review syndication and customer-segment routing layer run on N2 at $1,500/month.

Month-to-month, no annual commitment. Cancel any time. Median payback inside the 31-shop cohort is 6 weeks. If your shop does not see payback inside 90 days, we will personally tune the deployment until it does.