Back to home
Function · HR
Artellis builds a tool that assembles the whole onboarding pack from the role. You approve, and day one is ready.
The pain
Why this one is worth fixing
Every new starter’s first day is a last-minute scramble for accounts, hardware and paperwork. The checklist exists somewhere; it just never gets run cleanly because five different people own five different bits of it.
What Artellis builds
One approval kicks off the whole onboarding pack: accounts, hardware, contract, day-one schedule, intro pack. You approve, day one is ready.
How it works
- 01Takes the role and the start datePulls the right checklist, kit and access rules for that role: junior, senior, contractor, whichever.
- 02Requests accounts, orders kit, drafts the packIT tickets raised, kit ordered, contract drafted, intro pack written.
- 03You approve once, day one runs itselfThe starter walks in Monday to a laptop that works, accounts that exist and a schedule that makes sense.
Example artefact
What the output actually looks like.
New starter · Aoife M. · Mon 07 Jul
Pack ready · awaiting your approval
Accounts: Google, Slack, HubSpot, GitHub · requested.
Kit: MacBook Air M3, monitor, headset · ordered, arriving Thu.
Day 1: 09:30 welcome coffee · 10:30 team intros · 14:00 systems walkthrough.
Contract: drafted, ready to send via DocuSign on approval.
You edit and send.
Where it plugs in
Google Workspace / Microsoft 365BambooHR / PersonioDocuSignSlack / Teams
Guardrails
- Human-in-the-loop: nothing sends, signs or spends without you approving it.
- Your data stays yours, hosted in your tenant or a dedicated Artellis workspace, never used to train public models.
- Week-one build: something small and useful is live in the first week, before we scope anything bigger.
FAQ
How long until we see something working?
A first working version of the hr tool inside week one. Refinement and rollout happen after you have seen it work against your real inputs.
What do you need from us to start?
About 45 minutes to walk through the current flow, sample inputs (emails, files, screenshots, whatever you actually work from) and one person on your side who owns the outcome.
What happens if the AI gets it wrong?
Every draft goes to a human before it leaves the building. When you correct it, the tool learns your standard so the next one lands closer to right.
Bring us this workflow
One workflow. One week. Something working.

