Rune Ytreberg & Lars Adrian Giske: Building AI Tools for Investigative Journalism in Local News
Newsroom RobotsShow Notes
Translating a journalist's gut instinct into code—is it possible? In Norway, iTromsø—a long-standing regional newspaper known for its investigative journalism and deep local coverage—has found a way.
Their AI system, DJINN (Data Journalism Interface for News Gathering and Notification), acts like an experienced beat reporter, scanning hundreds of municipal documents and surfacing the most newsworthy leads. The impact? In their first week using DJINN, summer interns fresh out of journalism school produced five front-page stories—on a beat that usually takes years to master.
In this episode of Newsroom Robots, Rune Ytreberg and Lars Adrian Giske join host Nikita Roy to talk about iTromsø’s structured approach to AI-driven reporting and how they built tools that strengthen their local journalism.
Rune leads iTromsø’s data journalism lab, where he has been developing AI-driven editorial solutions for 70 local newspapers within the Polaris Media Group since 2020. And Lars is the Head of AI at iTromsø and led the development of DJINN. Since its launch in 2023, 36 newspapers across Norway have adopted DJINN, sourcing documents from nearly half of all Norwegian municipalities.
Key topics include: •How a small newsroom built AI tools to strengthen investigative journalism •Why their AI systems are designed for specific beats like urban planning and fisheries, reducing hallucinations and increasing precision. •Embedding editorial expertise in AI development •How their fisheries database flagged irregularities and how their urban planning system transformed local accountability coverage.
This is just Part 1 of our deep dive into how iTromsø is using AI to power investigative reporting. In Part 2, Rune and Lars will discuss their latest project: AI-powered research assistants that will proactively surface investigative leads for their journalists.
Sign up for the Newsroom Robots newsletter for episode summaries and insights from host Nikita Roy. Hosted on Acast. See acast.com/privacy for more information.
More from Newsroom Robots
For most of journalism’s history, the article has been the atomic unit of news: a fixed container, written once and served the same way to everyone. That’s beginning to change. AI is moving out from behind the scenes, where it quietly powered efficiencies, and into the interface itself, where it can assemble, personalize, and adapt the news to each reader.
At The Seattle Times, an AI tool identified a new prospect and helped close additional ad revenue in a single day. The Seattle Times is one of 11 news organizations participating in the Lenfest AI Collaborative and Fellowship Program, funded by OpenAI and Microsoft. Through this initiative, AI engineering fellow Rajesh Barade worked with the advertising team to address their challenges and developed a prospecting agent. This tool enables sales representatives to enter a category or focus area, identify businesses spending in that market, find decision-makers, access advertising spend data, and generate personalized outreach.
For years, the aggregator model was simple: curate the best journalism from thousands of publishers and send audiences their way. Now that contract is being rewritten, and Yahoo News is one of the most interesting places to watch it happen.
AI is settling in as infrastructure within newsrooms, a layer quietly reshaping how journalists discover information, how stories move through production, and how audiences increasingly expect news to reach them.
Most major newsrooms have now moved beyond early experimentation with AI. The main challenge now is determining how to govern effectively, scale consistently, and strategically position AI across the entire organization—while maintaining public trust as a central priority.