Articles 2.0
How journalists can use vibe coding to make their stories interactive. Plus: McClatchy’s AI backlash, a German court ruling on Google AI Overviews, and more.
With vibe coding, any journalist can turn a data-heavy investigation into a clickable, interactive experience in minutes—without writing a single line of code. This week’s column makes the case for vibe coding as a practical journalism tool: describe what you want, let the AI build it, and walk away with something readers can actually explore.
Also, my next AI Quick Start class for those just getting started with AI is tomorrow! We won’t shy away from the latest stuff, though—Anthropic’s Fable 5 model will come up.
A MESSAGE FROM ADOBE
The new Adobe productivity agent orchestrates tools and models to generate images, text and rich content like presentations, podcasts and social posts, while also powering conversational PDF editing in Acrobat.
With new PDF Spaces capabilities, users can combine files, links and notes into interactive, shareable spaces for research, collaboration and content creation. VICE News, Kid Cudi and celebrity event planner Mindy Weiss are already using these tools to build trust and deeper engagement with their audiences.
Learn more: Do that with Acrobat: AI-Powered PDF workspaces | Adobe Acrobat
Vibe coding can turn a investigations into experiences
By Kris Krüg
Look, I’m going to be straight with you. The traditional article is powerful. But it’s only one way to present your reporting.
You spend weeks on an investigation. You publish 3,000 sharp words. But what happens to the data behind it? The full timeline? The quotes that didn’t fit?
What if you could turn that investigation into an interactive experience, complete with clickable timelines, hover-activated charts and tagged insights, in about 20 minutes?
With vibe coding, it’s possible.
What is vibe coding?
The term vibe coding came out of developer culture, but it is no longer just for developers. It’s for anyone who wants to tell a story that harnesses the power of coding.
When you vibe code, you’re building an application with the help of AI by focusing on what you want it to do. Rather than coding with HTML, JavaScript or other technical languages, a builder describes the user experience in plain language to a Large Language Model (or LLM).
You might type a prompt like, “Build me an interactive timeline showing [x, y, z] events.”
Here are the five steps that I’ve seen succeed with journalists who have embraced vibe coding:
Read the full piece at The Media Copilot
Graduate from AI tools to AI agents
AI Quick Start is a one-hour live workshop for journalists, PR pros, and communicators who are ready to move past using AI as turbocharged Google and start putting it to work in real, practical ways.
In just 60 minutes, you’ll learn how to:
Sharpen drafts, edits, and ideas with a clear, repeatable prompting framework
Get real research done using deep research tools that read across the web for you
Build a custom GPT that learns your beat, your voice, and your workflow
Spot the AI traps (hallucinations, source misuse, and the prompts that lead you astray)
You’ll also get an introduction to agents, using AI to take on bigger tasks by operating apps just like you can. Once you go agent, you never go back.
📅 Class is Tomorrow — Friday, June 12 at 1 p.m. ET. This is the last chance to grab a spot before the session.
The Chatbox
All the AI news that matters to media*
A newspaper unionized over McClatchy’s AI byline policy
McClatchy told reporters at the Centre Daily Times it would use their bylines on AI-generated stories — whether they agreed or not. The reporters' response: form a union. According to reporting from Press Gazette, the AI byline policy became a direct catalyst for the organizing effort, which is one of the clearest examples yet of AI deployment triggering labor action inside a newsroom. The case puts a sharp point on the consent question: when management controls AI tools that affect editorial identity, workers may have no recourse except collective bargaining. (AI-assisted)
Reuters and Time are blocking all AI bots by default
Two major publishers are flipping the default assumption for AI crawlers: instead of allowing all bots and blocking the bad ones, Reuters and Time are now blocking every bot and only whitelisting the ones they explicitly approve, Digiday reported. The approach represents a meaningful shift in how publishers can exert control over who trains on their content. If the model spreads, it could change the negotiating dynamic between publishers and AI companies significantly. (AI-assisted)
German court rules Google liable for AI Overview errors
A German regional court has ruled that Google can be held liable when its AI Overviews feature produces factually false answers about a real person. The case, according to The Decoder, applies traditional defamation principles to AI-generated content at scale. If the ruling survives appeal, it could carry broad implications for how AI-powered search is regulated across Europe — and how publishers think about their own AI content liability. (AI-assisted)
*AI-assisted news items are drafted with AI and then carefully edited by Media Copilot editors.
 |
|