--- title: "Publisher Engagement Platform: Grow Session Depth When Traffic Won't Grow" description: Google referrals to publishers fell a third in a year (Chartbeat) and ad supply fell up to 40% in Q2 2026 (Digiday). The Artificial Poets Platform grows the metric still in your control — session depth — measured at +46% on enabled titles while comparable titles fell 16%. url: https://preview.artificialpoets.com/solutions/session-depth/ site: Artificial Poets type: page date: 2026-08-09T06:31:06+00:00 modified: 2026-08-18T02:10:14+00:00 image: https://preview.artificialpoets.com/wp-content/uploads/a13s-cards/1369-social-d16bdb88.png --- # Make Every Visit Worth More **Measured on live deployments** "Traffic keeps falling and I can't stop it — how do I make the visits I still get worth more?" You can't stop the traffic falling. What is still yours is whether a visit ends on the page it started on or becomes a session. That is the number the Platform moves: +46% multi-page sessions on enabled titles while comparable titles fell 16%. [See it on my numbers](/request-a-demo/) · [Check your single-page rate](/resources/session-depth-assessment/) Horse & Rider · Ride TV · Equine Network · Equus Magazine · The Score · Equine Network Lockup ## The problem, in your numbers Traffic decline is a market condition. Session depth is a product decision. - **−33%** Google traffic to publishers, in one year; −38% US (Chartbeat / Press Gazette) - **−40%** Publisher ad supply, Q2 2026, up to (Digiday) - **−16%** Multi-page sessions over nine months on titles that change nothing (our panel) ## Watch the divergence Multi-page session share over nine months, against the unchanged titles in the same network. Only the pre and post averages are measured; the connecting lines are illustrative. Same network, same audience, same weeks. One thing changed on two titles. - **10.3% → 15.1%** Multi-page session share on Platform-enabled titles, month one to month nine (+46%) - **12.0% → 10.1%** Multi-page session share on the unchanged comparison titles over the same window (−16%) ## The evidence, at its honest tier - **Multi-page sessions** — +46% on enabled titles (10.3% → 15.1%) vs −16% on comparison titles (12.0% → 10.1%) - **Largest single-title lift** — +19.1% in the first quarter, +4.0% at steady state — both published; plan on the second - **Verified three ways** — a comparison group (the entire eligible set), a window-sensitivity sweep, and a four-week serving pause that returned the metric to baseline and recovered on resume - **Traffic did not grow** — Sessions and users were flat — this is a depth result, and we say so **Introducing** ## Artificial Poets Platform One engine behind every solution on this site. It learns your archive and your readers, then acts inside your CMS, your templates and your ad stack. - It learns your archive: **Every story you have published, current again** — The engine understands each piece by what it is about, not when it ran or where it was filed. A feature from 2019 competes for the next slot on merit with one from this morning. - It reads the visit: **What a reader wants, without asking** — Interest builds from what someone actually does in the session. No login, no third-party cookies, nothing leaving your domain. Useful on the second pageview, not the tenth visit. - It chooses: **The right next read, not the popular one** — Someone comparing products and someone following a running story want different things. A most-read list gives both the same five links and serves neither. - It serves: **There before the reader leaves** — The feed, the recommendations, the search answer and the signup ask all run on the same engine, in your templates and your ad stack. Any slot that arrives with them is yours to sell. - It proves: **A lift you can defend, or we say so** — Every deployment runs beside titles that did not get it, plus a serving pause. That is how a result becomes a number you can take to a board instead of a vendor claim. ## FAQ ### Will this work on my content and audience? The measured lift held on every device and every acquisition channel except direct — which fell less than the comparison group's direct, and is printed. Mobile, the hardest segment, moved +48% against a −23% comparison decline. See the segment breakdown. ### How is this different from the related-posts module our CMS already ships? Related-posts modules match metadata: same category, same tags, newest first. The Platform matches meaning and the reader's in-session interest, then serves the next article as they scroll. The difference shows up in behaviour: continuation past the fourth served article runs 70 to 82%, and the measured contrast is +46% against −16% on unchanged titles. ### Does this need a big, fresh archive to work? No. The engine reads each piece by what it is about, not when it ran: a 2019 feature competes for the next slot on merit with this morning's post. Evergreen-heavy enthusiast archives are where the measured results come from; a deep back catalog is an asset here, not a liability. ### What does the pilot look like, and what are the exit terms if the lift isn't there? A quarter and a JavaScript tag — no migration, no redesign, nothing to unpick. You will know from your own analytics, not from us: we agree the metric and what counts as success before anything is switched on, and the baseline period gives you a real "before" to judge it against. Some titles will move less than others, and the honest ones say so. ### Does it hurt UX or Core Web Vitals? Nothing is forced on the reading experience: the next article renders in your own templates beneath the one being read, and readers continue voluntarily. Continuation past the fourth served article runs 70 to 82%, a curve forced pageviews do not produce. Density and layout stay yours. ### Does anything learned from our readers train something another publisher uses? No. Your behavioural data and your content stay yours and are not pooled into a shared model. Recommendations on your pages draw on your own library and your own readers' behaviour; nothing learned from your audience serves anyone else's pages. ### What does integration take from our engineering team? Authorization, CMS access, infrastructure access: that is the list. The integration is a JavaScript tag per title, carried out by our team using documented standard implementations; no migration, no redesign. Your side's real work is agreeing the metric before the four-week baseline starts. ## Related - [Session Depth Assessment](https://preview.artificialpoets.com/resources/session-depth-assessment/) — Two numbers from your analytics place your single-page rate and depth distribution against a continuously measured publisher panel. - [Horse & Rider Grew Pages Per Session 19% Without Growing Traffic](https://preview.artificialpoets.com/customers/horse-and-rider/) — In the first quarter after enabling the Platform, one in six Horse & Rider readers went past the first page, up from one in ten. Three comparable titles moved less than a quarter of a point. - [The Second Pageview Is the Last Metric You Still Control](https://preview.artificialpoets.com/blog/second-pageview-metric/) — Session depth is the share of your sessions that reach more than one page — and in 2026 it is the only major publisher metric whose fate is still decided on your own site. You cannot make search send the readers it used to send. You cannot reprice a programmatic market that is shedding volume. What you can decide is what happens in the thirty seconds after a reader lands. - [Serve the Next Article Before They Leave](https://preview.artificialpoets.com/use-cases/infinite-article-feed/) — "What happens after a reader finishes an article — can the next one just be there?" ## See how this works on your titles Thirty minutes on your analytics. We tell you what share of your sessions stop at the first page, and what this would realistically move first for a setup like yours. You leave with the annotated read. No deck. [See it on my numbers](/request-a-demo/) How these numbers are made: [the measurement method](/solutions/measurement/). Figures from a multi-title publisher network measured continuously, August 2025 to May 2026. Last updated August 15, 2026. ## Questions this page answers ### What is session depth? Session depth is how many pages a visit reaches: whether it ends on the article it started on or becomes a multi-page session. It is the engagement lever still fully in a publisher's control while referral traffic declines. On the network we measure, multi-page session share went from 10.3% to 15.1% over nine months on enabled titles. ### How does the Artificial Poets Platform grow session depth? The Platform learns your archive by meaning, builds an anonymous interest profile for each reader during the visit, and serves the next article as the reader scrolls. It runs as a JavaScript integration inside your templates and ad stack: no migration, no redesign. Continuation past the fourth served article runs 70 to 82%, a curve forced pageviews do not produce. ### How much does the Artificial Poets Platform cost? There is no public price list; pricing follows the size of the network and the formats involved. The commitment is designed to be small: a JavaScript tag, a four-week measurement-only baseline, and a quarter to judge the result from your own analytics against success criteria agreed before serving starts. ### Who is session depth for? Publishers whose traffic decline is a market condition: enthusiast networks, multi-title portfolios, and news sites losing search and social referrals. If you are judged on sessions, engaged time, or revenue per session, depth is the metric this platform moves. The published results come from live deployments on enthusiast media titles. ### What are the alternatives for growing session depth? Recommendation widgets from ad networks monetize exits to other sites; the Platform serves only your own library on your own domain. Building in-house takes 18 to 24 months and an ML team you must hire and keep. Changing nothing has a measured cost too: comparable titles that changed nothing fell 16% over the same nine months. ### How do I get started with the Artificial Poets Platform? Authorization, CMS access, infrastructure access: that is the list. Four weeks of measurement-only baseline follow, collection and indexing with no AI serving, then enablement on a named day. Eight weeks from authorization to a measurable effect, with integration carried out by our team using documented standard implementations.