Archive
making stories, research and source material accessible
The archive is how past stories, research, and source material stay findable and usable. A good archive lets a newsroom build on its own work instead of starting over. AI can help tag, search, and surface old material, so the question is how reliably it finds what you need and how it handles sensitive material held over time.
Questions to explore
- How do you store and find past stories, research, and source material today?
- What do you struggle to locate again once a story is published?
- Where could AI help tag, search, or resurface relevant material from the archive?
- How would you confirm that an AI search returns the right material and is not missing key items?
- What sensitive archived material needs extra care before it goes into any AI tool?
Expert voices
“Turn forgotten archives into searchable, summarized, and findable material.”
“In unstable contexts, archiving is protection: automated backups prevent regimes from scrubbing critical stories.”
“Internal archives are often so hard to access that reporters search the internet instead and end up with low-quality sources. AI could unlock those high-quality, fact-checked materials.”
“Would it be possible to train an LLM on our own archive to maintain our editorial style?”
Things to consider
- An AI search can miss items as easily as find them, so do not assume it is complete.
- Sensitive source material in the archive needs protection over the long term.
- Good tagging and structure decide how useful the archive will be later.
Pull Archive when it is relevant and set it aside when it is not. Pair it with the other Journalism cards, lay them out on a table, and use the questions above to get everyone on the same page. Capture what you discuss on sticky notes or in a shared doc.
More Journalism cards
