{"id":900721,"date":"2026-04-21T18:12:45","date_gmt":"2026-04-21T23:12:45","guid":{"rendered":"https:\/\/newsycanuse.com\/index.php\/2026\/04\/21\/why-the-guardians-first-reader-facing-ai-product-isnt-a-chatbot\/"},"modified":"2026-04-21T18:12:45","modified_gmt":"2026-04-21T23:12:45","slug":"why-the-guardians-first-reader-facing-ai-product-isnt-a-chatbot","status":"publish","type":"post","link":"https:\/\/newsycanuse.com\/index.php\/2026\/04\/21\/why-the-guardians-first-reader-facing-ai-product-isnt-a-chatbot\/","title":{"rendered":"Why The Guardian\u2019s first reader-facing AI product isn\u2019t a chatbot"},"content":{"rendered":"
\n
\n
\n

By Tim Peterson<\/a><\/span> \u00a0\u2022\u00a0 March 31, 2026<\/span> \u00a0\u2022<\/p>\n<\/div>\n

<\/p>\n<\/p><\/div>\n

\n

This article is part of Digiday\u2019s coverage of its Digiday Publishing Summit. More from the series \u2192<\/a><\/p>\n

Subscribe: Apple Podcasts<\/a> \u2022 Spotify<\/a><\/p>\n

The Guardian didn\u2019t want to build an AI chatbot. Not a reader-facing one anyway. Not at the risk of that chatbot misrepresenting the news publisher\u2019s journalism and undermining readers\u2019 trust.<\/p>\n

\n

\u201cWe\u2019re not going to die if we don\u2019t build a chatbot tomorrow. We need to be really clear about what the threats are externally, but ultimately what we have is something that\u2019s worth protecting,\u201d said Chris Moran, head of editorial innovation at The Guardian, during a live recording of the Digiday Podcast at the Digiday Publishing Summit in Vail, Colorado, on March 23.<\/p>\n

While not a chatbot, The Guardian has begun to roll out its first reader-facing AI product. But it doesn\u2019t really look like an AI product.\u00a0<\/p>\n

Called Storylines, the product is an AI-generated spin on the related links module common to publishers\u2019 pages. It currently appears on a subset of The Guardian\u2019s so-called \u201ctag\u201d pages, which typically list articles related to a given topic, such as \u201cTrump,\u201d in reverse-chronological order. Amid this article feed is an unassuming box with a selection of related articles threaded to a given narrative or storyline.<\/p>\n

\u201cIt\u2019s generating from a list of the most recent 200 articles on this tag what it thinks the three big storylines are across those articles. And it\u2019s really good technology for this. It\u2019s good at applying narrative to something and decoding it,\u201d said Moran.<\/p>\n

The Storylines box is clearly labeled as AI-generated, though the only text generated by AI are three subtitles across the top of the box that define the three related storylines.\u00a0<\/p>\n

\u201cIt\u2019s a curatorial tool, fundamentally. What it\u2019s designed to do is highlight the journalism and showcase the journalism,\u201d Moran said.<\/p>\n

To ensure the AI tool accurately highlights the journalism, The Guardian does not provide the large language model with the actual article text. Only the headlines. That way the publisher controls the context of the information that the LLM can work with to limit the potential for hallucinations.\u00a0<\/p>\n

\u201cWhat you\u2019re saying to the machine is \u2018I want you to pay attention to what we said.\u2019 This is about what our human editors said,\u201d said Moran. He added, \u201cit stops the machine from noticing a reference to Brad Pitt in the 17th paragraph of something and assuming [the entire article] is about that.\u201d<\/p>\n

To further rein in the LLM, The Guardian had a team of 20 senior editors evaluate multiple instances of its output. \u201cWe were asking them to look at a set of at least 10 of these across the course of two weeks and giving us quite detailed feedback,\u201d Moran said. The Guardian\u2019s data science team then applied that feedback to model updates.<\/p>\n

Even after all that, The Guardian\u2019s Storylines tool remains in limited testing on only 10 tag pages. The publisher expects to roll it out more broadly, but never across its entire corpus.\u00a0<\/p>\n

\u201cWe\u2019re never going to turn this on on 27,000 tag pages. And there are certain kinds of tag pages we\u2019re just going to avoid,\u201d Moran said. And of course, given the atomic threat of generative AI to the media industry, there is the nuclear option. Said Moran, \u201cWe obviously have a very large red button which says, \u2018Turn this off.\u2019\u201d<\/p>\n<\/div><\/div>\n

\n

\n More in Media<\/span>
\n <\/h3>\n<\/p><\/div>\n<\/div>\n

Tim Peterson
Read More<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

By Tim Peterson \u00a0\u2022\u00a0 March 31, 2026 \u00a0\u2022 This article is part of Digiday\u2019s coverage of its Digiday Publishing Summit. More from the series \u2192 Subscribe: Apple Podcasts \u2022 Spotify The Guardian didn\u2019t want to build an AI chatbot. Not a reader-facing one anyway. Not at the risk of that chatbot misrepresenting the news publisher\u2019s<\/p>\n","protected":false},"author":1,"featured_media":900722,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[673,35328],"tags":[5719,110826],"class_list":{"0":"post-900721","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-first","8":"category-guardians","9":"tag-first","10":"tag-guardians"},"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/posts\/900721","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/comments?post=900721"}],"version-history":[{"count":0,"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/posts\/900721\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/media\/900722"}],"wp:attachment":[{"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/media?parent=900721"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/categories?post=900721"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/tags?post=900721"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}