AI Agents
Discovery Express

Customer ops

Appointment Agent

Books, confirms and reschedules appointments by voice and WhatsApp, and fills the gaps a cancellation leaves.

In productionReviewed September 3, 2026
Voice · Appointment
Demo data

  1. Patient

    I need to move my Thursday appointment, something came up at work.

  2. Agent

    I can do Tuesday at 9:40 or Friday at 4:15, both with the same doctor. Fasting is still required, eight hours before.

  3. Scheduling system · appointment moved to Friday 4:15 pm · Thursday slot released to the waiting list

  4. Handoff to a person

    The patient then asked whether to stop a medication: transferred to the nurse line. The agent gives no clinical answer.

VoiceScheduling systemYour EHRGoogle Calendar / Outlook
KPI it moves
No-shows down 18% to 34%Measured
Channels
VoiceWhatsAppWeb
Integrates
  • Scheduling system
  • Your EHR
  • Google Calendar / Outlook
  • Telephony
A clinic receptionist with a headset at the scheduling screen, a patient waiting behind
Customer ops

What it does

Every appointment confirmed. Every cancellation refilled.

Where it lives

Your cloud, your repo, your IP.

1. Receives 2. Looks up 3. Decides 4. Acts 5. Escalates 6. Learns

Channels

  • Voice
  • WhatsApp
  • Web

Appointment Agent

03Decides

Systems it integrates

  • Scheduling system
  • Your EHR
  • Google Calendar / Outlook
  • Telephony

A person on your team

01

Receives

Answers the call or the message, identifies the person and understands what they need booked.

02

Looks up

Reads real availability, the rules of that service and any preparation the appointment requires.

03

Decides

Offers two or three slots that fit the rules instead of reading the whole calendar out loud.

04

Acts

Books, sends the confirmation with instructions, and reminds at the intervals you set.

05

Escalates

Passes clinical questions, urgent cases and anything outside the protocol to your staff.

06

Learns

Tracks which reminder timing actually reduces no-shows per service and adjusts the schedule.

KPI it moves

Measured, with the source.

Every figure has a row in the Proof Ledger: source, date, owner and client permission.

Proof Ledger
Measured

Measured

18% to 34% lower

No-show rate

Range observed across deployments of this agent, Sep 2026

Measured

40% to 60%

Cancelled slots refilled

Range observed across deployments of this agent, Sep 2026

Measured

60% to 80%

Booking calls handled without a person

Range observed across deployments of this agent, Sep 2026

Reviewed September 3, 2026

How it is governed

Every action has an owner, an eval and a limit.

Set in the Blueprint, enforced by the Govern layer of the platform.

Govern · Approval queue
Demo data

Waiting for a person

Same-day urgent slot · 16:30 · cardiology

The service lead approves the change

Weekly eval

Passing

Booking accuracy against the calendar

98.9%

Last 8 runs
95.8% → 98.9%

Voice comprehension within the weekly target

Limit, enforced

Call 8812 handed to reception after 2 attempts

Human approvals

  • Booking rules and overbooking policy owned by operations
  • Any change to a same-day or urgent slot

Typical evals

  • Booking accuracy against the calendar of record
  • Comprehension and containment on voice per week

Limits

  • No clinical advice, triage or diagnosis
  • No access to the record beyond the fields booking needs

Time to production

8 to 12 weeks

of pilot to production under a KPI Contract, after a Blueprint of 1 to 2 weeks

The agent already runs in production elsewhere, so the 2 to 4 weeks of tuning inside the pilot go to your policies, your data and your systems, not to the model.

DaCodes delivery standard, Sep 2026. Integration is the long pole, not the model.

How we deploy
The four phases
Commitment gate

  1. 01Discovery Express

    2 sessions, no cost

  2. 02Blueprint

    1 to 2 weeks

  3. 03Pilot

    8 to 12 weeks

  4. 04Scale & Managed

    Continuous

  • Pilot, first 8 weeks
  • Up to week 12 of the pilot
  • This agent: 2 to 4 weeks of tuning, inside the pilot
  • Commitment gate: the KPI decides Scale

Proof and demo

What backs the label.

Proof Ledger note

In production

Measured in a real deployment and logged in the Proof Ledger with source, date and owner.

Reviewed September 3, 2026

Where this agent sits on the maturity policy

  1. Reference architecture
  2. Pilot
  3. In productionToday

The Discovery Express shows this agent on your data, live. Two sessions, no cost.

See this agent with your data

Related agents

Same function or industry.

All agents
A courier handing a package at a doorstep in Monterrey
In production

Customer ops

Order Tracking Agent

KPI it movesMeasured

Where is my order tickets down 60% to 78%

FAQ

Direct answers.

No. It books, confirms, reschedules and explains preparation. Any clinical question goes to your staff, and that limit is enforced in the Govern layer, not only in the prompt.

It releases the slot and offers it to the waiting list in priority order, on the channel each person prefers. Between 40% and 60% of released slots get refilled across deployments.

It runs in your cloud, reads only the fields a booking needs and masks identifiers before any model call. Retention and residency follow your policy and LFPDPPP.

Which process do we automate first?

Two discovery sessions, no cost, and you leave with two or three quick wins whether or not you build with us.

We reply in under one business day.

Loading the form