Prompt library - Article writing

Prompt library - Article writing
Photo by Thought Catalog / Unsplash

💡
Prompt for creating a well researched article and publish it

Write and publish a long-form interactive analysis article for the InAgentic blog.

Title: "Which European cities will survive the AI disruption — and which won't?"
Slug: european-cities-ai-disruption-ranking
Category: Analysis
Tags: European cities, AI disruption
Read time: 10 min read
Date: May 2026

Use web search to research all facts, statistics, scores, and city data before writing.

SCORING FRAMEWORK

Score 10 major European cities (1M+ population) across 9 dimensions using a mix of
quantitative data and qualitative assessment. Score each dimension 1–10.

The 9 dimensions:

  1. Job resilience — automation-resistance of the existing workforce, NOT wage level
  2. Retraining infrastructure — government and private programmes available
  3. Adaptive capacity — institutional strength and sector diversity
  4. Entrepreneurship — startup density, new business formation, VC culture
  5. Geographic mobility — access to multiple labour markets, transport links
  6. Funding availability — VC investment, public grants, private capital
  7. Cost of living — scored INVERSELY (higher score = more affordable)
  8. Digital infrastructure — broadband speed, remote work readiness
  9. Language accessibility — English prevalence, ease for international workers

Choose 10 cities with 1M+ inhabitants representing a geographic and economic spread
across northern, central, and southern Europe.

Research and assign scores based on real 2025/2026 data. Justify scores briefly.

ARTICLE STRUCTURE

  1. Opening — AI displacement is already underway. The question is which cities give
    workers the best chance to survive and adapt.

  2. The Framework — explain the 9 dimensions and why they were chosen. Surface the key
    tension: city economic strength ≠ worker outcome quality.

  3. The Automation-Resistance Paradox — argue that high-wage cities are not necessarily
    resilient cities. AI targets exactly what professional services require. Physical,
    dexterous, and caring work is harder to automate. Use researched examples.

  4. City Snapshots — a brief card for each city: 2–3 key strengths, 1 key weakness.

  5. The Interactive Tool — a fully functional JavaScript weighting tool (see below).

  6. The North-South Divide — identify the pattern that emerges across weightings and
    explain the structural reasons behind it.

  7. London's Paradox (or whichever city presents the most instructive contradiction
    between private sector strength and worker outcome) — explore in depth.

  8. Why Retraining Is Weighted Low by Default — explain that government programmes
    lag rapid disruption; private capital and entrepreneurs fill the gap first.

  9. What This Means For You — practical guidance for knowledge workers thinking
    about location decisions in the next 5 years.

  10. Close — note that scores combine quantitative data with qualitative judgement
    and invite challenges.

INTERACTIVE TOOL REQUIREMENTS

Build a fully functional JavaScript weighting tool embedded in the article HTML.

  • Each of the 9 dimensions has a slider from 1 (not important) to 10 (critical)
  • City weighted scores recalculate in real time as sliders move
  • Rankings re-sort with smooth animation
  • Each city card shows: flag, dimension score badges, bold weighted total
  • Rank-change arrows show movement vs equal-weight baseline

Include these preset buttons that set all sliders simultaneously:

  • Crisis default (private capital moves fast, govt lags — weight cost of living and
    funding highest, retraining lowest)
  • Govt safety net (weight retraining and adaptive capacity highest)
  • Startup founder (weight entrepreneurship and funding highest)
  • Mobile professional (weight geographic mobility and language highest)
  • Low income worker (weight cost of living and job resilience highest)
  • Equal weight (all dimensions set to 5)

Include a score reference table summarising top and bottom scorers per dimension.

Include a footnote explaining the job resilience scoring methodology.

STYLE & TONE

Editorial and analytical. Opinionated but evidence-based. No AI buzzword soup.
Pull key arguments out as styled blockquotes.
City snapshots as a card grid.
Dark header styling on tables, alternating rows.

DEPLOY via FileDone MCP:

  • slug: european-cities-ai-disruption-ranking
  • category: Analysis
  • keywords: European cities AI disruption, AI job displacement Europe, AI resilience
    ranking, future of work Europe 2026
  • description: We scored 10 major European cities across nine dimensions of AI
    disruption resilience. The results challenge almost every assumption about which
    cities are safe.
  • excerpt: We scored 10 major European cities across nine dimensions of resilience.
    Then we built a tool so you can weight what matters to you.
  • featured: true