Purpose
~5 minChapter 17 treats publication as the beginning of a map’s second life. This lab asks you to design a maintenance pipeline that keeps a prompt-built web map coherent, accessible, documented, and responsibly updateable after release.
Core ideaMaintenance is stewardship: automation handles routine checks, monitoring notices drift, and humans preserve meaning.
Setup: Choose a Live or Hypothetical Map
~15 minMap to maintain
Purpose:
Audience:
Data update frequency:
Likely dependencies: data source / basemap / model / API / fonts / hosting
Design decisions worth preserving:
Design decisions allowed to evolve:
What failure would most damage trust:
Part 1 - Map the Deployment Chain
~20 minDescribe the deployment chain for this map: prompt, map specification, files, repository, hosting, data sources, and public URL. Identify where intent is documented and where it could be lost.
Part 2 - Design a Small Boring Automation Pipeline
~30 minDesign a small maintenance automation pipeline. It should regenerate the map when inputs change, run basic checks, and report what happened. Include checks for layer rendering, legend completeness, credits/disclosures, contrast, broken links, data schema changes, and successful deployment. Do not allow automation to redesign the map.
Part 3 - Monitor Drift and Version Integrity
~30 minCreate a drift monitoring plan. Watch for visual drift, data drift, technical drift, and semantic drift. Define what counts as acceptable change, what requires human review, and what must be versioned with a note explaining intent.
Part 4 - Add Human-in-the-Loop QA
~25 minCreate a human review checklist for this map. Include questions no automated check can answer: whether the map still makes sense, whether it feels clear, whether accessibility still feels inclusive, whether the legend read-aloud is understandable, whether keyboard/touch behavior works, and whether public interpretation might have shifted.
Part 5 - Set a Rhythm of Review
~20 minSet a sustainable review rhythm. Specify what runs automatically, what gets checked weekly/monthly/quarterly, what triggers an alert, what deserves immediate intervention, and what should be allowed to age gracefully.
Part 6 - Write the Maintenance Dossier
~30 minCompile my work into a Maintenance Dossier. Include deployment chain, automation routine, drift monitoring, versioning rules, human QA checklist, accessibility care plan, review rhythm, preservation/evolution principles, and graceful obsolescence criteria.
Submission
~20 min- Map maintenance profile
- Deployment chain
- Small automation pipeline
- Drift monitoring plan
- Human QA checklist
- Review rhythm
- Maintenance Dossier
- 400-600 word reflection on stewardship over control
How to Do Well A friendly self-check: aim to keep automation modest, document version changes, distinguish drift types, treat accessibility as ongoing care, define sustainable review rhythms, and explain which design principles must be preserved versus allowed to evolve. Think of this as the success path while you work, not a gotcha at the end.
Psst! Before You Turn This In...
~3 minAnd once more, ad nauseam, with feeling: the prompt is not the judgment.
Do the tiny-but-mighty judgment check. If these answers are fuzzy, revise the map idea before polishing the prompt.
- Purpose: Can you say what this map helps someone understand or decide?
- Evidence: Can you point to the data, source, or context behind the claim?
- Omission: Did you leave out, downplay, or defer anything that would distract or mislead?
- Risk: What could be overstated, exposed, or misunderstood?
- Human check: What must be verified outside the LLM?
- Stop rule: What would make you redesign, withhold, or simplify this map?
Ian's recurring refrain Prompt frameworks are scaffolds. The LLM can suggest, critique, and surprise you; you still own the cartographic judgment.
Reference
For use with Prompt Cartography: Interactive Web Map Design with LLMs, CRC Press. www.promptcartography.com