![]() |
We have two stories this week about AI tools that give reporters access to information they wouldn’t have, or that it would be extremely time-consuming for them to get, otherwise.
Neel wrote about Roganbot, “a testbed for ‘visibility tools’ that help keep tabs on the internet”:
Roganbot works on a simple premise: it listens to [the podcast Joe Rogan Experience] for you, creates a searchable transcript linked to timestamped audio, and breaks episodes down into key topics, notable quotes, potential controversies, and suggested fact-checks. It can, in essence, be extremely online for you, and then you can ask it questions about what it found in its internet rabbit hole.
Roganbot is a testbed for a larger concept that Swanson and Waddell call “visibility tools” — AI-powered research tools that can help journalists keep tabs on specific topics without having to invest hours sifting through transcripts or data sets. The use cases for visibility tools depend on context: While Roganbot could be helpful for someone trying to keep up with the manosphere, a local journalist might find more utility in having a similar bot listen to city council meetings instead.
And Andrew wrote about some of those visibility tools in practice in newsrooms:
Increasingly, AI transcription tools powered by large language models (LLMs), like LocalLens, are assisting journalists who cover local government — whether that be with auto-generated summaries of town halls meetings, school district proceedings, or even hearings in state legislatures.
By most accounts, these tools aren’t able to generate publishable stories, or even publishable transcripts. But they are helping local reporters find sources, stay informed about public meetings they can’t attend in real time, and expand the scope of their coverage.
“We are going to be in the rooms where we need to be, where the big decisions are being made, but we can’t be everywhere all the time,” said Eric Gorski, the managing editor for local news at Chalkbeat, who has been coordinating the newsroom’s use of these tools. “The summaries are springboards for more reporting. It’s not a replacement for coverage, and we’re not trusting AI to get these things right. It’s more like a news tip.”
Find those stories, and more, below.
— Laura Hazard Owen
![]() |
Local newsrooms are using AI to listen in on public meetingsChalkbeat and Midcoast Villager have already published stories with sources and leads pulled from AI transcriptions. By Andrew Deck. |
![]() |
You can learn a conference’s worth of data journalism through these NICAR tipsheetsFrom AI to OSINT, maps to the sports section, it’s a data journalism jubilee. By Joshua Benton. |
![]() |
“More alarming by the day”: New York Times investigations editor on the legal threats faced by news publishers“The rhetoric and actions that Trump and his allies take at a national level are being mimicked across the country at a much smaller level. Whether they’re Trump supporters or not, they’re taking cues from the President of the United States.” By Sarah Scire. |
![]() |
How Trump’s cuts are crippling journalism beyond the United StatesAccording to a USAID factsheet now taken offline, the agency funded training and support for 6,200 journalists and assisted 707 outlets. By Gretel Kahn, Marina Adami Eduardo Suárez. |
![]() |
This AI tool could give newsrooms “eyes and ears where they don’t have them”Roganbot, created by two journalists, is the testbed for “visibility tools” that help keep tabs on the internet. By Neel Dhanesha. |