Skip to content

People operations

Reference build

Twelve coordinator hours back per hire

An agent that orchestrates multi-step, multi-system employee onboarding — accounts, access, equipment, paperwork — and chases what has not happened yet.

12hrscoordinator hours saved per hire

At a glance

Duration
17 weeks
Team size
1 person
Engagement
New build
Project type
AI & automation
Industry
B2B SaaS

The situation

The challenge

Onboarding is a dependency graph across systems that do not talk to each other, and the failure mode is silent: a step nobody completed, noticed on the new hire's first morning.

What we did

Model onboarding as a state machine with owners and deadlines per step, and make the agent responsible for chasing rather than for deciding.

The calls that mattered

  • Explicit state per step, not a checklist

    Each step has an owner, a deadline and a state. A checklist tells you what should happen; a state machine tells you what has not.

  • Escalation is the default outcome

    Anything incomplete escalates on a schedule rather than waiting to be discovered.

What changed

coordinator time saved per hire
12hrscoordinator time saved per hire
silent failures
0silent failures
  • 0 — every incomplete step escalates

Roughly twelve coordinator hours saved per hire, with nothing incomplete going unnoticed.

Services used

  • Onboarding state machine across HR, IT and access systems
  • Ownership, deadline and escalation model
  • Coordinator dashboard

What we would do differently

Every project has one of these. Publishing it is the point — a case study with no regrets in it is marketing, not evidence.

The orchestration mattered more than the intelligence. Most of the value came from modelling the process properly, and only a little from anything the model contributed.

Services used

More work

Ready to start?

Start a project like thisWork