Markdown

But like you said, data is...

I've been talking about data integrity for the last year and how important that is and how things like OKF and ARD may be solutions for that, turning things into Markdown so an agent can read it but still output it in a visual manner for us.

And again, the visual manner will be different for you and I because, like you say, NLP will make us relate to things in different ways visually.

I may like a pie chart, you like a bar chart, maybe as simple as that.

If you think of something like OpenClaw back in February, all of that stuff was coming out.

Really at the heart of what they were doing, what that technology was doing, was it would take some input, it would perform an action, and it would then do it repeatedly, and each time it did it, it would get a little better because it would update its Markdown files, its soul and its memory, to support a better execution next time.

And so that's sort of at the heart of this technology, but it's so hard to...

I found it very difficult to describe in the abstract unless there's a very clear use case to do it, and I think Matt's was really good.

Same time, we saw this huge spike in these AI assist agents coming to the markdown version of that page.

And that was really sort of the big aha moment for us that there was a big opportunity here for us to use that markdown page as a new piece of inventory that is highly valuable because those agents were operating on behalf of people that were coming in huge numbers over the first several days that the list launched to get that information.

And so that's when it really crystallized for us that we should go to Ally and we should talk to them about you should also have your version of a machine readable ad on that Markdown page the same way that we're presenting the content to the agents on behalf of the time editorial.

So with that, we quickly sprung into action.

We had been having these conversations, as you mentioned, Project Management Institute and Ally were the two that we launched with.

Have they spoken to you directly? Are you still partners? How is their interpretation differing from yours? And can there be a meeting of the minds here?

We did meet with Perplexity and we actually walked them through the entire process and everything that we've developed.

We showed them that example of looking at the source code on an HTML page versus looking at the Markdown page.

But ultimately, using it to audit some of your past work and just cleaning up your skills, cleaning up your agents, cleaning up your markdown files, I find that to be extremely valuable.

And it also has just cut out a lot of fluff.

If I look through a Markdown file of mine or I look through a skill of mine, I can't really tell, to be honest.

Is this helping? If I delete this, is this going to be problematic? So yeah, it's literally just slash cloud API prompt audit and it will go through.

You command shift the skills or the Markdown files you wanted to audit and it made a pretty big difference.

I think that's a great use case.

So many people going, it's great to audit it because obviously this stuff changes so quickly.

I don't know, Will, what's your experience?

When we remove all the lingo, the magical nerdy programming languages, tools, technologies, software development is about getting group of people together into the room or kind of like virtual room and then telling them and those people are probably from different backgrounds they can be engineers they can be user experience designers there can be project managers product owners domain specialists and we tell all those this group of people to to to think together and solve some problem that is what software development in principle is however the current tools are changing this very much because they are moving to this like very individual focused workflows so i decided that we want we we want tools that are actually allowing us to still collaborate in the context of ai tools that are interactive that have real-time multiplayer collaboration tools that are working on this higher level of abstraction, which is managing plans and documents, because that's how we work nowadays with AI.

Like Markdown is new programming language of the 2026.

It's probably the most popular language of 2026.

So this is what Japan is.

We need to build new product type of things.

And horizon three is the crazy ideas in the future.

So again, everyone knows that there will be Markdown multiplayer with AI.

things showing on the market in the next six months.

And in particular, ChatGPT will only reach their valuation based on their fundraising if they really build a healthy ads business and make a lot of money on shopping they've got to have a meta meets amazon multiple if you think that open ai is going to grow into their valuation just selling tokens are you kidding as prof g would say those people are going to grow up to have a shitty business like kroger or southwest airlines where there's sexy stocks until they're not because there's just no margin in that business the margin is content that people trust shopping recommendations that people rely on And I believe that ChatGPT will be very aggressive in protecting that against tomfoolery, so to speak.

And I'll give you a classic example, like Markdown language.

A lot of companies have said, hmm, we're going to take all of our pages and publish them in Markdown, put them out on the edge for the agents to see.

It worked for a minute, and then all of a sudden there's been adjustments to make sure that it doesn't work too much because it actually might pollute the value of the actual platform.

But I can see how that would get a lot of action.

Daniel, ¿cuál es el panorama de amenazas desde el equipo de inteligencia de Google?

El grupo de inteligencia de amenazas de Google publicó este miércoles un informe en el que documenta a un actor con motivación financiera que desplegó un framework multiagente, un chatbot de programación con IA, una inyección de prompts y playbooks de Markdown preconstruidos que de forma autónoma planificó, construyó y ejecutó una campaña masiva de robo de credenciales.

Es el relato forense más claro hasta la fecha de IA adversarial que pasa de la teoría a una infraestructura de ataque operativa.

Amber, la seguridad empresarial también avanza rápido.