AI Agents
Discovery Express

Operations

Shift Planning Agent

Builds the shift plan against demand, skills and the law, and covers the absence before the shift starts.

PilotReviewed September 3, 2026
WhatsApp · Shift Planning
Demo data

  1. Team member

    I cannot make the Saturday morning shift, my daughter is sick.

  2. Agent

    Understood, you are out of Saturday morning. I am offering it to the four people who are certified and rested, in fairness order.

  3. Time and attendance · shift covered in 12 minutes · rest rules respected · no overtime generated

  4. Handoff to a person

    Sunday cannot be covered without overtime: the manager gets the two options with their cost and decides.

WhatsAppTime and attendanceHR systemsDemand forecast
KPI it moves
Coverage and overtimeMeasured in pilot
Channels
WhatsAppInternal appsSlack / Teams
Integrates
  • Time and attendance
  • HR systems
  • Demand forecast
  • Payroll
A shift supervisor checking the shift board in a distribution center
Operations

What it does

Every shift covered before it starts.

Where it lives

Your cloud, your repo, your IP.

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

Systems it integrates

  • Time and attendance
  • HR systems
  • Demand forecast
  • Payroll

Shift Planning Agent

03Decides

Channels

  • WhatsApp
  • Internal apps
  • Slack / Teams

A person on your team

01

Receives

Takes the demand forecast, the roster and the requests for the coming week.

02

Looks up

Reads skills, certifications, availability, rest rules and the hours each person already has.

03

Decides

Builds a plan that meets coverage without breaking a rest rule or pushing anyone into overtime.

04

Acts

Publishes the plan for the manager to approve and offers open shifts on WhatsApp in fair order.

05

Escalates

Warns the manager when coverage is impossible without overtime or an exception, with the options ranked.

KPI it moves

Targets set, being measured.

These are the numbers we sign in the KPI Contract, not results, until the pilot closes.

Proof Ledger
Pilot targets

Target, being measured

50% to 70% fewer

Uncovered shifts

Pilot target set in the Blueprint and measured against your baseline during the pilot. DaCodes, Sep 2026

Target

Target, being measured

10% to 20% lower

Overtime hours

Pilot target set in the Blueprint and measured against your baseline during the pilot. DaCodes, Sep 2026

Target

Target, being measured

Under 30 minutes

Time to cover an absence

Pilot target set in the Blueprint and measured against your baseline during the pilot. DaCodes, Sep 2026

Target
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

Week 38 plan, Monterrey site · the site manager publishes

4 open shifts offered on WhatsApp

Weekly eval

Passing

Legal compliance of the generated plan

100%

Last 8 runs
96.9% → 100.0%

Fair shift distribution within target

Limit, enforced

Double shift for one person removed from the draft

Human approvals

  • The published plan, by the site manager
  • Any overtime or rest rule exception

Typical evals

  • Legal compliance of every generated plan
  • Fairness of shift distribution per person and month

Limits

  • It never publishes a plan that breaks a labor rule
  • No changes to pay, contract or seniority

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 Library agent it needs 2 to 4 weeks of tuning inside the pilot, most of it on your policies and your systems, not on 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

Pilot

Running today. The figures above are targets signed in the KPI Contract until the pilot closes.

Reviewed September 3, 2026

Where this agent sits on the maturity policy

  1. Reference architecture
  2. PilotToday
  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.

It proposes. The site manager approves the plan before anyone sees it, and every rest and overtime rule you load is a hard constraint, not a preference.

It offers the open shift on WhatsApp to the people who are qualified and available, in the fairness order you set, and stops as soon as one accepts.

The rules you load are constraints in the planner: rest between shifts, weekly rest, maximum hours, minors and certifications. Legal owns that file, versioned in your repo.

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