Plants along the windows of an office

Remind the people who have not finished

Drafted reminders for the overdue, sent only when you say so.

For
HRLegal / IT
Routine
Every week
Setup
Juno + 2 tools
You approve
every draft

What you get

The prompt

Written to ask before it assumes, check what already exists, and stop before anything goes live.

Works in Claude, ChatGPT, Copilot
Remind the people who have not finished:

Send a personal, non-shaming reminder to the people who have not finished an assigned training, after I have seen exactly who gets it and exactly what it says.

═══ ONE ROUND OF QUESTIONS ═══
Ask me in ONE message, then wait:
1. Which training. Find it by name (search_lms_content) and confirm.
2. Who counts as behind: not started, in progress, or both; and whether to limit it to a team, department, or the people I manage.
3. The tone: gentle, firm, or final notice.
4. The deadline to mention, if any.

In that same first message, also ask me my role and the team I support, and which team chat we use. Then check each one is connected in this chat; if not, I'll connect it or upload an export. Never guess what is in it.

═══ THE LIST, HONESTLY SOURCED ═══
If learning data is enabled on our account, pull the learners behind on this training from it (learning_activities_query), scoped as I said, and show me the count and a named sample of up to eight. If it is not enabled, say so in one line and offer two ways in: I export the learner list from the training's analytics page in Juno and paste it, or I paste names or emails directly. Never guess, reconstruct, or invent who is behind. If the list is longer than you can show, tell me the total and where to see the rest in Juno.

═══ THE MESSAGE, THEN STOP ═══
Draft the reminder in the chosen tone: two to four sentences, assumes busy rather than negligent, one clear ask, the deadline if there is one, and a link to the training. No comparisons to colleagues, no completion percentages, no consequences I did not state, no promise of automatic follow-ups. Use only the personalisation fields the platform supports (list_notification_variables). Show me the recipients and the exact text and wait.

═══ SEND FROM THE CARD ═══
Open it for review (prepare_notification) with the recipients and text filled in; I send from there. Offer to pre-draft the next, firmer version so it is ready if we need it. If the deadline should move for everyone still open, say what that changes before you do anything.

Rules throughout: the list comes from real data or from me, never from guesswork; recipients and text shown before anything opens; every send fires from a card I confirm; a private nudge, never a public callout; talk in product terms, not tool names.

Routine: after the first run, offer to repeat this every week. If this assistant can run scheduled tasks, set one up only after I approve it; if not, give me a one-line prompt I can re-run.

Your AI asks you

  1. Q1Which training. Find it by name (search_lms_content) and confirm.
  2. Q2Who counts as behind: not started, in progress, or both; and whether to limit it to a team, department, or the people I manage.
  3. Q3The tone: gentle, firm, or final notice.
  4. Q4The deadline to mention, if any.

The routine

  1. 01

    Connect

    Juno and the tools below

  2. 02

    Answer

    the questions, one message

  3. 03

    Review

    the draft or the view it builds

  4. 04

    You approve

    before anything goes live

Routine: Every week. The prompt offers to set it up as a scheduled task in your assistant, only after you approve.

What it connects

  • JunoRequired
  • SlackNative
  • Microsoft TeamsNative

Your AI assistant reads the tools it can reach and drives Juno.

Where this Journey Play works