Back to home
Function · Scheduling
Artellis builds a tool that spots the gaps and proposes cover from who is actually free, one click to confirm.
The pain
Why this one is worth fixing
A gap in next week’s rota becomes a 9pm round of phone calls. You know who’s off, roughly, but not who’s actually free, so the person who answers the phone gets the shift, whether it makes sense or not.
What Artellis builds
Gaps spotted early, cover proposed from who’s actually available and contracted, one click to confirm.
How it works
- 01Spots gaps a week aheadReconciles roster, time-off requests and contracted hours, flags before it becomes an evening call.
- 02Proposes cover that actually fitsNo double-bookings, no over-hours, no ‘she’s off on Thursday’ mistakes.
- 03One click confirms and notifiesConfirmed swaps are logged, staff get notified in their preferred channel.
Example artefact
What the output actually looks like.
Next week · 4 gaps, 3 cover swaps proposed
Confirm to notify staff
Tue 14:00–19:00 · Cover: Aoife (available, +3 hrs to weekly total)
Wed 09:00–13:00 · Cover: Ben (available, within contract)
Fri 17:00–22:00 · Cover: Ciara (available, weekend swap)
Sat 10:00–14:00 · No cover yet, 2 candidates suggested.
You edit and send.
Where it plugs in
Deputy / Planday / When I WorkGoogle CalendarWhatsApp / SMSPayroll for hours check
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 scheduling 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.