AI Agents
Discovery Express

Operations

Fleet Check-Call Agent

Calls every driver on schedule, logs the status in the TMS and flags a delay in minutes, not at the end of the shift.

Reference architectureReviewed September 3, 2026
Check call · Unit 42
Demo data
Live call · 00:41

  • Good morning, this is the dispatch assistant for Route 18. Are you on schedule for the 14:00 delivery?

  • Running late, about twenty five minutes. Traffic on the highway.

  • Understood. I am moving the delivery window to 14:25 and notifying the customer. Anything else to report?

  • No, all good.

ETA updated in TMS

14:00 → 14:25 · customer notified on WhatsApp · dispatcher alerted

Own voice stack · about $0.035 per 15-min call, internal measurement, Aug 2026

TMS
KPI it moves
80 to 90% of check calls automatedTypical target
Channels
VoiceWhatsApp
Integrates
  • TMS
  • GPS telematics
  • Route sheets
  • Telephony
A dispatcher on the phone at dawn, trucks parked outside the window in Monterrey
Operations

What it does

Every driver called. Every delay logged in minutes.

Where it lives

Your cloud, your repo, your IP.

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

Systems it integrates

  • TMS
  • GPS telematics
  • Route sheets
  • Telephony

Fleet Check-Call Agent

03Decides

Channels

  • Voice
  • WhatsApp

A person on your team

01

Receives

Loads the day's routes and check-call schedule from the TMS and the dispatcher's exceptions.

02

Looks up

Reads GPS position, ETA and the last status before each call so it asks only what the data cannot tell.

03

Decides

Classifies the trip as on time, at risk or stopped, from the call and the telematics together.

04

Acts

Logs the status in the TMS, updates the ETA and confirms the next check-in with the driver.

05

Escalates

Alerts the dispatcher on delays, incidents and unreachable drivers, with location and call summary.

06

Learns

Picks up route patterns and preferred call windows, and tunes its scripts with the operations team.

KPI it moves

Typical targets, no result yet.

The first KPI measured in a client pilot is what promotes the label.

Proof Ledger
Typical targets

Typical target

80 to 90%

Check calls automated

Typical target for a reference architecture, not a result. DaCodes, Sep 2026

TargetNo result yet

Typical target

Under 15 minutes

Delay detection

Typical target for a reference architecture, not a result. DaCodes, Sep 2026

TargetNo result yet

Stack cost, measured

$0.035

Voice cost per 15-minute call

DaCodes voice stack, 15-minute call, internal measurement, Aug 2026. Stack cost, not a client result

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

Route change requested · trip 3310 · waiting for the dispatcher

Unit 42 · Route 18

Weekly eval

Passing

Status accuracy against GPS

96.4%

Last 8 runs
93.3% → 96.4%

Daily sample · call completion within target

Limit, enforced

Call to unit 17 held · driver in a rest period

Human approvals

  • Escalation rules and dispatcher contacts approved by operations
  • Any change to a route or delivery window

Typical evals

  • Status accuracy against GPS on a daily sample
  • Call completion and driver comprehension rate

Limits

  • Calls only inside the driver-hours rules you set
  • No route changes without a dispatcher

Time to production

8 to 12 weeks

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

As a reference architecture, plan for the upper end of the pilot range: integration to your systems takes most of the time, and the first measured KPI is what promotes the label.

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: plan for the upper end
  • Commitment gate: the KPI decides Scale

Proof and demo

What backs the label.

Proof Ledger note

Reference architecture

No result yet

No client pilot has closed with a measured KPI. The first one promotes the label.

Reviewed September 3, 2026

Where this agent sits on the maturity policy

  1. Reference architectureToday
  2. Pilot
  3. In production

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 maintenance technician checking readings on a tablet beside a CNC machine
Reference architecture

Operations

Telemetry Watch Agent

KPI it movesTypical target

Unplanned downtime 15 to 25% lower

FAQ

Direct answers.

Because no client result has been measured yet. The voice stack it runs on is measured ($0.035 per 15-minute call, Aug 2026) and the design comes from discovery work with logistics operators, but the KPIs on this page are typical targets, not results.

Same job, your cloud, your data and a voice cost of $0.035 per call instead of per-minute fees. It writes to your TMS; nothing lives in a vendor console you cannot leave.

It retries inside the cap you set, tries WhatsApp, and escalates to the dispatcher with the last GPS position. An unreachable driver is a first-class alert, not a silent gap.

Read access to the TMS routes and the telematics feed, write access for status and ETA, and telephony or WhatsApp Business. Integration is scoped in the Blueprint.

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