Loading video...

Video Failed to Load

Go Home

SEOs, your competitors may be covertly switching their content from HTML to markdown for AI agents. You can analyze by auditing their Accept Headers. Here's the process:

15,811 views • 8 days ago •via X (Twitter)

8 Comments

Paul Sanders's profile picture
Paul Sanders7 days ago

Covertly? lol Just use and tick the “content” checkbox. That accept header test is covered of course

Serge Bezborodov's profile picture
Serge Bezborodov7 days ago

We tested AI bots to see what request headers they actually send on real traffic. Surprisingly, nobody except one accepts Markdown. I personally don't understand this obsession with Markdown. Converting HTML to Markdown during parsing isn't a big deal.

Buswe's profile picture
Buswe8 days ago

Serving the markdown from the same URL with Vary: Accept keeps it off the index and normal crawlers still get the HTML.

Automate AI | E-commerce SEO's profile picture
Automate AI | E-commerce SEO7 days ago

Tested and approved

bnownlater's profile picture
bnownlater7 days ago

Gives me “amp version” vibes all over again.

Aviel A. Fahl's profile picture
Aviel A. Fahl6 days ago

I think that to the extent that we want agents to be able to take action on our sites, we shouldn’t rely on crutches but work on aria labels etc.

Michael Latulippe's profile picture
Michael Latulippe7 days ago

Interesting discussion here. In my opinion, I think JSON is the preferred language of ai agents, particularly for datapoints on a page. Markdown is more like a bridge for humans to copy over info to their AI for a chat discussion.

Joe Youngblood - SEO, Futurology, AI, Marketing's profile picture
Joe Youngblood - SEO, Futurology, AI, Marketing7 days ago

Should have this working (better) in Rocketship SEO for WordPress here soon. We've been doing it for about a year or so. ChatGPT and other LLMs sometimes try and work around it.

Related Videos

Here's how I'm running automated content engine in 2 files 1 markdown file = my wiki 1 html file = my dashboard that's the whole stack. [ the architecture, in plain words ]: LLM wiki = a single markdown file holding my audience DNA, 15 tracked creators, every viral topic from the last 30 days HTML artifact = a single page that reads that markdown file AND can trigger my agents the artifact and the agent talk to each other directly the wiki is the shared brain [ what I actually see when I open it at 9am ]: > 5 trending topics ranked by my audience-DNA fit > 3 KOL posts worth quoting today > last week's saved tweets (so I can ride waves that are still warm) > buttons: [draft tweet] [draft QT] [schedule] [log idea] 1. I click "draft tweet" on a topic 2. the artifact pings my agent 3. agent reads the wiki, drafts in MY voice, returns it to the artifact 4. I edit, schedule, done 15 minutes from morning coffee to 3 scheduled posts [ how to build the same in one evening ]: > step 1: dump your domain knowledge into ONE markdown file (audience profile, KOL list, content rules, voice guide, anything an agent would need to do YOUR job) > step 2: ask claude to build an html artifact that reads from that file ("here's my wiki, build me a dashboard with these views") > step 3: add buttons for the actions you do daily (draft, schedule, log, score, search — your workflow, not mine) > step 4: wire each button to call your agent via tool calls (so the artifact and the agent talk directly) the moment your artifact reads your wiki AND triggers your agents.. most SaaS tools you currently pay for quietly become unnecessary dashboards I used to pay $50/month for now sit in a single html file I can rebuild in 20 minutes every "I'll build a SaaS for this" idea you had last year is a 200-line file you write in an afternoon if you want to get the same content engine, just reply "CONTENT" and will send you in DMs later we're going from buying software to owning it.

Ronin

50,315 views • 5 months ago