One of the most widely circulated interviews from Cannes last week is Axios reporter Sara Fischer speaking with Cloudflare CEO Matthew Prince.
Cloudflare is a publicly-traded content delivery network (CDN) with a market cap of $62 billion.
-
See a clip from the interview on YouTube (17 minutes).
-
Read Axios coverage (June 19).
Mr. Prince makes his case that publisher content is turning into content for LLM chatbots with dwindling, reciprocal referral traffic. To be clear, Prince’s company sees this traffic through the technology Cloudflare sells to publishers, so he has an “axe to grind.”
Mr. Prince provided the following data on crawling behavior by large language model (LLM) owners:
-
Google: Six months ago: 6 pages crawled to 1 visitor sent to the publisher by Google. Today: 18 pages crawled to 1 visitor sent to the publisher by Google (which has now added AI Overviews).
-
OpenAI: Six months ago: 250 pages crawled to 1 visitor sent to the publisher by OpenAI. Today: 1,500 to 1.
-
Anthropic: Six months ago: 6,000 pages crawled to 1 visitor sent to the publisher by Anthropic. Today 60,000 to 1.
A logarithmically-scaled graphic doesn’t look much better for publishers, either.

Sell-side consultant Matthew Scott Goldstein observed the Cloudflare data on LinkedIn yesterday and said, “The internet’s business model is at a breaking point. Original content creators face a dire future as AI fundamentally changes how information is consumed.” Read more.
More from Mr. Prince:
-
On Google search results: “… they give you an answer right on the page and the official Google number [that Google co-founders] Sergey [Brin] and Larry [Page] used to brag about – how their job was to get people off google.com as quickly as possible – now, 75% of queries to Google get answered on Google, which means that if you were an original content creator, your information is getting summarized and then sold because they still put ads there but you don’t get that traffic anymore.”
AI and publishers – opportunity
AdExchanger’s Anthony Vargas reviewed how a publisher is seizing opportunity with AI by licensing their own “live” data.
Mr. Vargas reported yesterday, “… Benzinga struck a deal with Dappier, which operates a marketplace of AI tools and licenses data from publishers to train those tools. Dappier ensures that chatbot responses using Benzinga’s data link back to the original source, and it also shares revenue from ads placed in these responses.”
Dappier provided its pitch on X yesterday using Benzinga as the use case:
“Through Dappier:
– ”Developers can ingest Benzinga data via API / MCP”
– ”Attribution is automatic and monetization is built in”
– ”Revenue is shared via usage and ads—no scraping, no guesswork”
thought bubble: “Live” (or constantly updating) data is clearly opportunity for publishers courtesy of AI – and ad tech – given the aforementioned licensing example. The livestream of the consumer is addressed with help from the live stream of unique “live’ data.
And, AI solutions networks are the new retail media networks à la what Uber announced last Friday.
Clicks are dead
-
Axel Springer Aims to Boost Value With AI, Calls Time on Clicks-and-Ads Model (June 23) – The Wall Street Journal
- Axel Springer Presents its New Corporate Strategy (June 23) – Axel Springer
- “This isn’t AI versus human intelligence—it’s AI with human intelligence. AI and HI. It’s not either or. It’s both. Who combines the best of both intelligences in the most complimentary way will win.”
State of AI search
Media buying agency FOMO.ai led by Dax Hamman, formerly of iCrossing and Rubicon Project among other stops, has released a new white paper titled, “Report: The State of AI Search – July 2025.”
Download it here (email required).
In the press release announcing the new report which is an extension of Hamman’s agency, “This isn’t just a shift in the search results,” says Dax. “It’s a shift in who gets seen, who gets trusted, and who gets chosen.” Read more.
The report offers a mixture of analysis and industry voices opining on AI search including a thought-provoking section titled: “Why Now is the Time to Double Down on Content (Not Cut Back).”
Agency embrace of AI
Chief Innovation Officer Henry Cowling of S4 Capital creative agency Monks (was Media Monks) talked to Adweek’s Debbie Abrams Kaplan in a sponsored post published yesterday which also appears to be an extension of an “activation” by Cannes.
Thought bubble: check out the investment (i.e. sponsored) here by Monks/S4 in establishing an AI narrative for the agency…
From the article: “‘It might not be too soon to say advertising is in existential crisis,’ [Cowling] shared. The technology is fundamentally disruptive to the industry, ‘and I think the time for pretending that is not happening is past. The smarter players in our space are the ones who are living up to that reality and looking for the opportunities that are coming out of that disruption.” Read more.
OpenAI needs ad platform
Venture firm Greylock has started a new podcast called the “Intelligent Marketer” and, as its first guest, Mobile Dev Memo analyst and investor Eric Seufert reiterates his view, “There’s no chance that OpenAI doesn’t have a scaled ad platform in four years.”
Seufert explains:
“The thing is, OpenAI knows a lot about me. I bet you it can map what it knows to exactly the demographic features that people advertise against. It probably knows my age. It probably could guess my net worth or whatever, might guess my disposable income, could guess that I have kids. It knows all those things. Knowing that, then what would you want to do? Would you want to pass that along to some intermediary? No.
First of all, you probably can’t. You wouldn’t be able to package that up in a decipherable way and pass it along. But even if you could, you wouldn’t want to. You want to keep that. That’s gold. That is worth its weight in gold, that information.
So, you would build your own advertising system on top of that.”
Hear more on Apple Podcasts.
Meanwhile: Mr. Seufert isn’t buying some of the hype on agents and advertising.
He wrote yesterday on X, “The notion that advertising will be directed at personal commercial agents, rather than at consumers themselves, strikes me as a dead end for several reasons….” Read more.
AI Overview pub stats
New Research Ranks Quora as the #1 Most-Cited Website in Google AI Overviews (June 18) – press release from Semrush/Quora

the purchase funnel & AI
Search Engine Journal (SEJ) investigates the value of the click in today’s AI-infused search world.
SEJ Contributor and search marketer Frederick Vallaeys believes that “clicks will be more relevant because, unlike in the past, where a click was a user’s initial exploration of your offer, they will now be better informed land further along in their research by the time they visit your site for the first time.
Mr. Vallaeys cites Microsoft research which indicates AI may push consumers even further down the purchase funnel when it comes to clicks.
The Microsoft research team “found that purchasing behaviors increased by 53% within 30 minutes of a Copilot interaction, underscoring just how powerful, timely, and AI-embedded suggestions can be.”
Read “Google AI Mode And The Future Of Search Monetization: Ads, Prompts, And The Post-Keyword Era.” (June 23)
Prompt: How will publishers make revenue using AI in five years?
Response from Mistral’s LeChat:
Predicting exactly how publishers will generate revenue using AI in five years involves some speculation, but several trends and strategies are already emerging that are likely to continue evolving. Here are some potential ways publishers might leverage AI for revenue generation:
-
Personalized Content and Recommendations:
-
Dynamic Content Creation: AI can help create personalized content tailored to individual readers’ preferences, increasing engagement and time spent on the platform.
-
Recommendation Engines: Advanced AI algorithms can recommend articles, videos, and other content to users based on their behavior and preferences, driving more traffic and ad revenue.
-
-
Automated Journalism:
-
News Generation: AI can automate the creation of news articles, especially for data-driven stories like sports results, financial reports, and weather updates. This can reduce costs and increase the volume of content produced.
-
Real-time Updates: AI can provide real-time updates and breaking news, keeping readers engaged and informed…
-
More stuff
-
CMOs say AI platforms’ low profile at Cannes won’t happen again (June 23) – Digiday (subscription)
- Checking In on AI and the Big Five (Apple, Google, Meta, Microsoft, and Amazon) (June 23) – Stratechery
-
Is AI helping agencies break out? (June 22) – Ari Paparo, Marketecture
-
How AI agents and agentic AI differ from each other (June 12) – CIO

