Nota: The journalism-trained AI tool helping small outlets expand capacity
Share this story:
When Susan Catron first encountered AI in journalism, she was skeptical. As managing editor of The Current, a coastal Georgia outlet known for its in-depth journalism, she had seen what tools like ChatGPT could do — and how quickly they could get things wrong.
“I was the one screaming across the newsroom: ‘Don’t touch AI, leave it alone,’” Catron says.
She didn’t want a black box. If she was going to experiment with AI, she wanted a system her newsroom could control, one specifically trained on journalism, not the open internet. That search led her to Nota, an AI tool built by journalists for journalists.
“That was my selling point with Nota,” she says. “I don’t know what the other ones do. I just know I trust this one right now.”
Three reasons to use Nota
- Nota offers newsroom-specific AI tools for headline optimization, content summarization and social media formatting without generating original copy.
- Unlike general-purpose AI, Nota is built specifically for journalism workflows and integrates seamlessly with WordPress and other content management systems.
- The tool requires minimal setup (less than one hour) with ongoing maintenance taking just 15-30 minutes weekly.
Newsroom overview
The Current, based in Savannah, Georgia, covers the Peach State’s coastal communities as the region’s only nonprofit investigative newsroom. It launched in 2020 with the goal of filling the news vacuum left when local newspapers either folded or consolidated. The Current aims to rebuild trust in local news and hold public servants accountable.
The outlet is one of more than 500 nonprofit newsrooms in the Institute for Nonprofit News (INN) network. In a newsroom of 10 people, Catron manages a small team that must balance limited resources against the need for in-depth local reporting while handling all aspects of digital publishing.
Problem: Reporters responsible for digital production
Small newsrooms frequently encounter what Andrew Haeg, INN’s network product manager, calls the “fried and frozen” problem: Newsrooms are fried from years of running at maximum capacity and frozen by the fear of burning scarce time and resources on technology that doesn’t deliver.
This describes The Current exactly. Catron’s team was stretched thin keeping up with the mechanics of digital publishing. The Current’s reporters were responsible for crafting SEO-optimized headlines, creating newsletter summaries and managing tags and metadata.
Catron believed that long-term sustainable growth required new revenue streams and digital expansion. But the time spent on repetitive but necessary publishing tasks was already eating into the deep reporting that justified the newsroom’s existence.
For small newsrooms like The Current, this creates an impossible choice: spend precious time on publishing mechanics or focus on the journalism that serves communities.
Solution: AI help designed for newsrooms
Nota, a web-based suite of AI tools including headline optimization, content summarization for distribution and social media formatting. Unlike general-purpose AI tools, newsrooms can implement Nota without installing new software or learning complex systems.
Nota CEO Josh Brandau, former chief marketing officer at the Los Angeles Times, designed Nota specifically to reclaim the hours journalists spend on repetitive tasks like SEO, headline writing and social media formatting.
The journalism focus goes deeper than understanding newsroom workflows. Unlike general-purpose AI tools trained on vast internet content, Nota’s underlying model is built on journalism-specific data.
“We use very ethical foundational models, and we’re only accessing data that we have rights to,” Brandau says. This targeted training results in hallucination rates of “way less than 10 percent ”— a crucial improvement over general-purpose AI tools like ChatGPT or Claude.
Brandau describes Nota’s approach as layered: open-source foundations combined with proprietary data-cleaning technology, an in-house editorial board and training from experienced journalists. The company offers feedback collection as an opt-in process to continuously improve suggestions.
Nota prioritizes eliminating adoption friction. The company offers demo sessions and extensive documentation. The tools integrate directly into multiple content management systems, like WordPress and Arc XP, and offer browser extensions for flexible workflows.
Despite the fast setup, Catron was determined to take things slowly. She started by testing Nota’s headline feature, which offers three suggestions that editors can accept, revise or ignore. Over time, the system learns from these choices, tailoring suggestions to the newsroom’s voice and preferences.
“It’s only as good as what we put in it,” she says. Well-reported and well-written articles yield better AI outputs, and skilled editors remain essential for catching small errors that pop up.
Impact: Optimizing digital content in less time
At The Current, Nota’s impact has been measurable. The tool now handles most of the newsroom’s SEO tasks — generating headlines, excerpts, tags and slugs that previously consumed hours of staff bandwidth each week. The team uses Nota’s suggestions for social captions about half of the time.
“I don’t even remember how much we spend on it a month, but I’m sure it has saved me that much time,” Catron says.
She sees potential in using Nota to update community calendars, a task her newsroom currently lacks capacity for and one that could open new revenue streams.
At the network level, INN has leveraged Nota to expand the reach of member content. INN newsrooms generate approximately 26,000 stories monthly, many under open licenses for republication, but insufficient resources often limit wider distribution.
INN uses Nota to create automated workflows that summarize member stories into editorially vetted excerpts. These summaries feed into services like Text Rural — an SMS news service for rural communities — and On the Ground, a curated weekly digest of local political stories. The entire process demands minimal newsroom involvement, requiring just 15-30 minutes weekly for review and approval.
“You could effectively support a really good product for your audience in minimal time,” Haeg says. “That just wouldn’t be possible without AI — in this case, Nota.”
Security and privacy
Nota addresses two critical concerns for newsrooms considering AI adoption: data security and editorial control. Unlike general-purpose AI tools that may train on user content, Nota operates on a closed-loop system that doesn’t use newsroom content for model training without explicit consent.
The platform employs enterprise-grade security measures aligned with SOC 2 Type II standards, including data encryption in transit and at rest, secure authentication with SSO support and role-based access controls that ensure only authorized users can view or manage content.
For newsrooms with strict privacy commitments to sources and subjects, Nota maintains a zero-data retention policy for training purposes and stores data only as long as necessary for platform functionality. The platform’s transparency features, including usage reports and granular access controls, help newsrooms maintain oversight of how their content is being handled.
Verdict: Good tool for smaller newsrooms
Nota won’t replace journalists, but it provides targeted, reliable solutions designed specifically for small, resource-strapped newsrooms. For publications like The Current, the tool offers a way to expand digital capacity without compromising editorial integrity.
Nota offers a grant-backed pricing tailored to the needs of small, independent newsrooms. Qualifying outlets (those with fewer than seven full-time newsroom employees and annual revenue under $250,000) can access their suite of AI tools for $99/month. Small business plans start at $349/month.
Other newsrooms that could benefit from Nota include resource-strapped local outlets seeking to expand digital capacity, nonprofit news organizations with limited technical staff, and publications that prioritize editorial control over AI-generated content.
As Catron prepares to welcome the next cohort of summer interns to The Current’s newsroom, she plans to instill both opportunity and healthy skepticism about AI tools.
“I’m going to put the fear of God into them about a few things,” she says with a laugh. “AI can allow us to get better and grow more trust. But it could also kill that trust in milliseconds.”
Alternatives: General LLMs
General-purpose LLMs: For cash-strapped newsrooms, tools like ChatGPT, Gemini and Claude offer a budget alternative as they offer free versions. Custom versions trained on an outlet’s content could replicate some of Nota’s capabilities, though this DIY approach requires significant trial-and-error and lacks dedicated support or journalism-specific training.
In-house systems: Media organizations like The New York Times, Bloomberg and Hearst Newspapers have built proprietary AI systems tailored to their specific workflows and scale. This approach offers maximum control and customization but requires substantial technical resources.
Share this story:
