The Philadelphia Inquirer built Scrape, an AI tool to surface hyperlocal news
The Philadelphia Inquirer needed a way to find newsworthy stories from fragmented local sources like municipal meetings and Facebook pages. One editor was spending 12 hours a week just gathering leads. They built Scrape, an AI tool trained on the editor's manual tip sheets, with daily feedback loops. After months of refinement, Scrape became critical infrastructure for six newsletters, used by nearly 20 journalists. The case study shares lessons on grounding AI in real workflows and encoding editorial judgment.
Scrape evolved from a small experiment to “load-bearing and critical infrastructure” for six (and soon, eight) newsletters, with nearly 20 journalists across the newsroom following its output.
- syntaxing
I like this so much. Maybe I’m romanticizing but hoping tools like this give local news a chance against monopolies like Sinclair Broadcasting.
- mmooss
> Early on, the team tried to balance quality with the high cost of searching many small, scattered sources. They discovered that prompting can implicitly control search depth and behavior, but only after trial and error.
I don't understand the cost here. The number of sources should be relatively tiny - it's not a general Internet search. The amount of data scraped would seem to be relatively tiny - how much data is there on suburban-county, PA?
- calvinmorrison