Service booking & workshop capacity

Fill workshop capacity without an advisor on the phone all day

Workshop capacity is perishable: an unfilled bay cannot be sold later. Yet service advisors spend their day on reminder calls, reschedules, and status questions instead of the customers in front of them — and the bookings that do get made are often the wrong duration for the work. This blueprint runs the outreach and booking loop against real capacity, and routes warranty and safety conversations to a certified advisor.

AI WORKERSORCHESTRATED PROCESSHUMAN AUTHORITY3 roles, trust-scoped6 stages, each with an owner1 decision ownerService outreach workerBooking workerStatus worker1Detect dueService outreach…2Reach outService outreach…3Scope the workBooking worker4Match and confi…Booking worker5Keep informedStatus worker6EscalateCertified service…Certified service…CONTROLS AROUND EVERY STAGE4 guardrails · 4 decision rules · 4 channels · tamper-evident audit
The blueprint at a glance — worker roles feed the orchestrated stages, and the dashed paths are the escalations into human authority.
The team
3 AI worker roles escalating into 1 human decision owner.
The process
6 orchestrated stages, each with a named decision owner.
The channels
Voice, SMS, WhatsApp, Email on one shared context.

The shift

What breaks today, and what changes

The challenge

  • Advisors lose the day to reminder calls, reschedules, and status enquiries while bays sit empty.
  • Bookings are made without matching job type to duration or technician skill, so the schedule breaks.
  • Reminder outreach happens in batches when someone has time, not when the service is actually due.

What changes

  • Service-due outreach runs on time, on the channel each customer responds to.
  • Slots are matched to job type, duration, and technician skill, so the schedule holds.
  • Warranty, recall, and safety conversations reach a certified advisor with context.

The team

Every seat has one job and a defined level of autonomy

This is what gets configured in Team Canvas: role-scoped AI workers, the humans they escalate into, and a trust level on each connection that sets what a worker may do on its own. Trust starts tight and widens on evidence.

AI workers

  • Service outreach worker

    Contacts customers when service is actually due, on their preferred channel.

    Owns
    Outreach and consent state
    Trust level
    Acts within policy — consent-bound and frequency-capped
  • Booking worker

    Matches the work required to a real slot with the right duration and skill.

    Owns
    Slot selection and confirmation
    Trust level
    Acts within policy — books only compatible slots
  • Status worker

    Answers “is my car ready?” from live workshop state and flags approvals needed.

    Owns
    In-service transparency
    Trust level
    Acts within policy — read-only, no cost approvals

Human decision owners

  • Certified service advisor

    Owns warranty, recall, safety, and additional-work authorisation.

    Owns: Technical and commercial authority

The process

The conversation starts the work. The workflow finishes it.

Each stage records the decision that was made and the role accountable for it — which is what makes the run reviewable afterwards rather than a black box. Where the platform executes a stage rather than a person or agent performing it, that is named too, and accountability still sits with the role.

  1. 1

    Detect due

    Service due, recall outstanding, or customer-initiated?

    Service outreach worker

    Run by workflow

  2. 2

    Reach out

    Is contact permitted, and on which channel does this customer reply?

    Service outreach worker

  3. 3

    Scope the work

    What work is needed, and what duration and skill does it require?

    Booking worker

  4. 4

    Match and confirm

    Which real slot fits, and is the customer confirmed with reminders?

    Booking worker

  5. 5

    Keep informed

    Has workshop state changed, or is additional work awaiting authorisation?

    Status worker

  6. 6

    Escalate

    Warranty, recall, safety, or cost approval? An advisor owns it.

    Certified service advisor

Decision rules

The non-negotiables encoded in the workflow, not left to a prompt.

  • Warranty, recall, and safety language routes to a certified advisor immediately.
  • Only slots compatible with job duration and technician skill may be offered.
  • Additional work and any cost above the agreed estimate require advisor authorisation.
  • Outreach respects consent state and frequency caps on every channel.

Controls & guardrails

What makes this safe to run in production, and provable afterwards.

  • Approved service facts with certified-advisor routing on warranty, recall, and safety.
  • Capacity rules that prevent incompatible bookings.
  • Cost-approval gates before any additional work.
  • Consent capture and frequency caps on all outreach.

Platform capabilities

What this blueprint runs on

Nothing here is bespoke. Each blueprint is a configuration of the same platform, which is why the second one you launch reuses the governance you already reviewed.

Channels

  • Voice
  • SMS
  • WhatsApp
  • Email

Systems it reads and writes

  • Dealer management system
  • Workshop scheduling
  • Vehicle & service history
  • CRM

Measurement

What we instrument from day one

These are the measurements the pilot puts in place, not benchmark results. You set the targets against your own baseline — and the same instrumentation is what decides whether a worker's trust level widens.

Capacity utilisation

Bays filled vs available

The commercial metric for this blueprint: how much perishable workshop capacity actually gets sold.
Booking accuracy

Duration vs actual

Compares booked duration against actual job time, which is what determines whether the schedule holds.
Reminder conversion

Due to booked

Tracks how many service-due customers convert to a booking, by channel and timing.

Rollout

How this one goes live

A deliberately narrow start, supervised, with autonomy widened per role once the record supports it.

  1. Weeks 1–2

    Inbound booking on one site

    Handle inbound booking and status questions for a single site against live workshop capacity.

  2. Weeks 3–4

    Service-due outreach

    Add consent-bound outreach triggered by actual service-due data rather than batch campaigns.

  3. Week 5+

    Multi-site and status updates

    Extend across sites and switch on proactive in-service status updates with advisor routing for authorisations.

Questions we get asked

Service booking & workshop capacity, in practice

Can it handle warranty or recall questions?
It recognises them and routes to a certified advisor with the vehicle and conversation context attached. Warranty, recall, and safety questions carry technical and legal weight, so they are outside the workers’ scope by design.
How does it avoid double-booking the workshop?
The booking worker reads live workshop scheduling and offers only slots compatible with the job’s required duration and technician skill. Booked-versus-actual duration is instrumented, so mismatches show up as a tunable signal rather than a broken schedule.
Can it authorise extra work found during a service?
No. The status worker can tell a customer that additional work is awaiting authorisation and flag it, but any cost approval above the agreed estimate is a certified advisor’s decision.

What changes in Automotive

Service capacity is matched to job type and duration, and warranty or safety language routes to a certified advisor.

Read the full Automotive analysis

Related blueprints

Next step

Build this team around one measurable win.

We map your version of this process, compose the worker roles, connect your systems, and agree the escalation points with the people who own them — then run it supervised.