Back to home
Function · Project Management
Artellis builds a tool that drafts the honest client update the moment a date moves; you edit and send.
The pain
Why this one is worth fixing
Slippage stays hidden until it is a crisis, because nobody wants to write the awkward update. So the date slides quietly, the client finds out late, and trust takes the hit that the timeline never did.
What Artellis builds
The moment a date moves on the plan, the honest client update is drafted for you: cause, mitigation, revised date. You edit and send.
How it works
- 01Watches the plan for movementNotices when a milestone slips on the tracker or in a status thread, the same day it happens.
- 02Drafts the update in your voiceNames the cause, the mitigation and the revised date, in plain language, no corporate hedging.
- 03You edit and sendOne click sends, logs the revised date on the plan, and notes what changed and why.
Example artefact
What the output actually looks like.
Re: Phase 2 timeline · update
To: Client · draft, awaiting your edit
Hi Mark,
A quick honest update on Phase 2: we are 3 working days behind the plan. The slip is on our side. The integration turned out larger than scoped.
Mitigation: I have added a dev for next week. Revised go-live: Friday 27 June (was Tuesday 24).
No change to Phase 3 dates. Happy to jump on a call if useful.
Richard
You edit and send.
Where it plugs in
Asana / Jira / MondayGmail / OutlookGoogle Drive / SharePointSlack / 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 project management 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.

