The Information Lab Logo
Build your Team
The Blog

Dashboard Week Day 4 Wikimedia API AI Promting

Brief:

The brief today was to build an Alteryx app that builds an HTML trend analysis report based on a user input. We had the choice of two API's and I decided to go with the Wikimedia API which contains Wikipedia page info.

Process:

  1. Reading through API documentation and identifying specific format requirements. For example dates had to be formatted: 27/08/2026 ->27082026.
  2. Built Alteryx Workflow.
  3. Added user actions to turn into an app.
  4. Numerous prompt iterations.

Challenges:

  1. Main challenge was over engineering anytime I tried to be too specific and include every instruction for how I wanted things done the html output would get truncated and refuse to load. This was solved by simplifying my prompt.
  2. Date axis on charts not working had to manually force a library inclusion.
  3. LLM generation streams appended markdown code fences (````html`) to the top of the raw text response, rendering visible backtick artifacts on the published page. So I implemented string stripping rules in both the prompt instructions and an Alteryx REGEX_Replace() clean-up formula prior to writing the .html file.

Here is my final workflow:

And here is the user interface:

Overall this was my final output:

Executive Analytics Dashboard
Analytics Dashboard
Wikimedia Pageviews
Author:
Ben Hayward
View Profile
Powered by The Information Lab
1st Floor,
25 Watling Street,
London, EC4M 9BR
1st Floor, 25 Watling Street, London, EC4M 9BR
+44 (0) 8453 888 289
INFO@THEINFORMATIONLAB.CO.UK
About
Apply
Locations
The Team
Coaches
Blog
Events
Privacy Policy
Terms of Use
Cookie Policy
Subscribe
to our Newsletter
Get the lastest news about The Data School and application tips
Subscribe now
© 2026 The Information Lab