Skip to main content
All example use casesIllustrative example

Water-point dashboards with breakdown alerts

A WASH NGO wants automated dashboards and alerts when a tap stand or latrine block stops working across 30 camps.

The challenge

A WASH NGO collects water-point functionality data in KoBo across 30 camps. Staff build reports by hand each week, so breakdowns are often spotted late. The team wants automated dashboards and an alert when a tap stand or latrine block goes down.

Kind of support

  • Data pipeline design
  • Dashboard review
  • Alert rules

How the mentorship could run

  1. Weeks 1 and 2: review the KoBo forms and agree a clear definition of a working and a broken water point.
  2. Weeks 3 and 4: set up an automatic export from KoBo into a shared database or spreadsheet, with checks for missing and duplicate submissions.
  3. Weeks 5 and 6: build one dashboard per camp and one overview, and test them with the staff who will use them each week.
  4. Weeks 7 and 8: add alert rules for breakdowns, decide who receives each alert, and hand the setup over with written instructions.

What to have ready before you apply

  • Your current KoBo forms and a sample export
  • The weekly report you build today, so the dashboard can replace it
  • Who must act on a breakdown in each camp
  • The tools your team already uses, such as Power BI, Excel or Google Sheets

Risks to plan for

  • Alerts that fire too often get ignored. Start with a small number of clear rules and adjust them after a few weeks.
  • A dashboard is only as current as the data. Agree how often each team submits, and show the date of the latest submission on every view.
  • Staff turnover is high in camp settings. The handover needs short written instructions, not knowledge held by one person.

What a good result looks like

Breakdowns are seen within a day, not at the end of the week. Staff stop building the weekly report by hand and use the time to fix water points.

More example use cases

  • Country: Colombia

    Sector: Cash assistance

    Finding duplicates across three cash programmes

    An INGO wants to find duplicate and likely wrong records across three programme lists, without building a surveillance tool.

    Time: 2 hours per week, 6 weeksIllustrative example
  • Country: Jordan

    Sector: Education

    Arabic reading practice with teacher review

    A learning centre wants an LLM to draft Arabic reading exercises, with a teacher checking everything before a child sees it.

    Time: 2 to 3 hours per week, 10 weeksIllustrative example
  • Country: Ukraine

    Sector: Shelter

    Building damage from drone and satellite imagery

    A shelter NGO wants to classify building damage from imagery so field teams visit the worst-hit areas first.

    Time: 1 to 3 hours per week, 12 weeksIllustrative example
  • Country: Nepal

    Sector: Information management

    A safe assistant over SOPs and guidance notes

    An information management officer wants to build a retrieval assistant over their organisation's SOPs, safely and on a small budget.

    Time: 1 hour per week, 8 weeksIllustrative example

Know more

Want to know more before you apply? Write to contact@theaiexpertgroup.com and a member of the Mentor Council will reply.