AI Agents
Discovery Express

People & talent

Onboarding Agent

Runs the first thirty days of a new hire, from paperwork and access to the questions nobody wants to ask twice.

In productionReviewed September 3, 2026
WhatsApp · Onboarding
Demo data

  1. New hire

    I start Monday and I still do not know where to go or what to bring.

  2. Agent

    Monday 9:00 at the Polanco office, reception on floor 4, official ID. Two documents are still missing from your file, and I can take them here.

  3. Workday · 2 documents received · access requests opened for email, repo and VPN · owners notified

  4. Handoff to a person

    VPN access is still pending 24 hours before the start date: HR and the manager are told, with the owner named.

WhatsAppWorkdayHR systemsIdentity provider
KPI it moves
Ready to work on day oneMeasured
Channels
WhatsAppSlack / TeamsEmail
Integrates
  • Workday
  • HR systems
  • Identity provider
  • Payroll
A new employee receiving a laptop at an IT service desk on her first day
People & talent

What it does

Paperwork, access and answers ready before the first day.

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

  • Workday
  • HR systems
  • Identity provider
  • Payroll

Onboarding Agent

03Decides

Channels

  • WhatsApp
  • Slack / Teams
  • Email

A person on your team

01

Receives

Starts the moment the offer is accepted in the HR system, in the person's language.

02

Looks up

Reads the role, the site, the contract type and the checklist those three imply.

03

Decides

Works out what is missing, in what order, and who has to move for the person to start on time.

04

Acts

Collects documents, opens the access requests, books the first sessions and answers the repeat questions.

05

Escalates

Tells HR and the manager when a document, an approval or an access will miss the start date.

06

Learns

Uses the thirty day check-in to find where the process breaks and fixes the checklist there.

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

85% to 96%

New hires fully set up on day one

Range observed across deployments of this agent, Sep 2026

Measured

3 to 5 hours less

HR hours per new hire

Range observed across deployments of this agent, Sep 2026

Measured

90% or more

Documents complete before the start date

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

SAP access for a new hire starting Monday · the system owner decides

Request filed in the identity provider

Weekly eval

Passing

Checklist complete at the start date

98.0%

Last 8 runs
94.9% → 98.0%

Answers checked against the HR policy of record

Limit, enforced

3 access requests filed · 0 granted by the agent

Human approvals

  • Every access grant, by the system owner
  • Contract, salary and benefits data, by HR

Typical evals

  • Checklist completeness at the start date
  • Answer accuracy against the HR policy of record

Limits

  • It requests access, it never grants it
  • No salary or performance data in any message

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 recruiter reviewing interview notes beside a stack of resumes in a Monterrey office
In production

People & talent

Voice Interviewer

KPI it movesMeasured

1,000 calls per month to 1,000 per hour

FAQ

Direct answers.

It opens the request with everything the owner needs to decide, and follows up until it is done. The grant itself stays with the system owner.

WhatsApp before the start date, Slack or Teams after it. Same agent, same thread, so nobody repeats a question they already answered.

Documents go straight into your HR system, never into a chat history, and identifiers are masked before any model call. Your cloud, your retention policy.

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