Using AI to find hidden data sources
How I found 56,273 hidden power outages in five minutes
The Dutch power outage website showed me a few records and no download button. Five minutes of digital digging later, I had 56,273 outages going back 13 years—none of them visible via normal search. Here's exactly how I did it — and how you can apply this method to your own research.
The Dutch grid operator Liander publishes resolved power outages on their website. You can browse them, click through locations, see details.
But you can’t download the data.
There’s no “Export to CSV” button. No public API documentation. Just a slick, JavaScript-heavy website that loads data dynamically — like a restaurant that shows you the menu but won’t let you take any food home.
The data is technically public — it’s on a website anyone can access. But it’s practically inaccessible for systematic analysis.
It’s like being invited to a library where all the books are behind glass. You can look, but you can’t actually read anything useful.
The Broader Context:
A 2022 study in Scientific Data found that over 60% of government datasets are “semi-open” — nominally public but requiring technical expertise to access. That’s not transparency. That’s a velvet rope.
I released AIWhisperer — shrink massive PDFs to fit AI upload limits. Sanitize before uploading to reduce risk of exposing sensitive data. It’s a first version. If you are a coder, please help improve it.
I’m also giving away prizes with total worth of $1000+ :
🎁 3x Perplexity Pro annual subscriptions , worth $240 each
🎁 1x You.com Team plan annual subscription, worth $300.00
To win? Just be a paid subscriber. That’s it. Already subscribed? You’re in. Not yet? Fix that before Feb 27th 2026. I’ll draw winners on Feb 28th 2026 .
The tool: Claude Code
Back to our problem. I used Claude Code to fix it. It is a command-line AI assistant made by Anthropic. Unlike web-based AI chat interfaces, it runs best in your terminal and can directly interact with your computer: reading files, writing code, executing commands, and fetching web content.
A terminal is a text-based interface for controlling your computer. On Mac it’s called “Terminal,” on Windows “Command Prompt” or “PowerShell.”
Think of it as having a research assistant who can also program — searching for data sources, writing extraction scripts, and running them — all while you describe what you need in plain language.
The key insight is that you didn’t need to learn programming. You need to learn how to describe what I wanted clearly enough that the AI could figure out the technical details. You are a developer, Claude is the vibecoder.
What is “Vibecoding”?
The term was coined by Andrej Karpathy (former OpenAI researcher, Tesla AI director) in early 2025. It describes a programming approach where you “fully give in to the vibes” — describing what you want in natural language and letting AI handle implementation details.
It’s not about understanding code. It’s about understanding your research question clearly enough to communicate it.
The exact conversation
Below is the complete conversation I had with Claude Code.
1. THE REQUEST
Fetch all data from https://www.liander.nl/storingen-en-onderhoud/opgeloste-storingen. Can't access via download.What I did: Stated the goal (get data), provided the source (URL), and expressed the obstacle (can’t access it). No technical specifications. No instructions on how to solve it.
2. CLAUDE HITS THE SAME WALL YOU WOULD
[Claude fetches the webpage — receives 72KB of HTML]
CLAUDE: Unfortunately, the page loads outage data dynamically via JavaScript. I can’t retrieve the actual data this way. The HTML structure is there, but the list of resolved outages is loaded separately by a component called “OutagesOnLocation.”
This is a common problem with modern websites: data is loaded via JavaScript/AJAX after the page loads. Simple HTTP requests only get the “empty” HTML skeleton, not the dynamically loaded content. Here are some alternatives: 1. Liander API — Liander might have a public API. Want me to search for an API endpoint? 2. Browser Developer Tools — If you open the page in your browser, you can use F12 → Network tab to see which API calls are being made. 3. Manual copy — You could copy the data from your browser. Should I search for a Liander API?What a normal person would experience: You visit the Liander website, see a nice interface showing outages, but there’s no download button. You can browse the data one page at a time, but you can’t export it. You’re stuck.
Claude hit the exact same wall. The difference is what happens next. What do you tell AI to try harder?
