Aug 26, 2026 · 39 min · 7 segments
**As AI Agents Rise, Security Must Come First with Nick Steele**In this episode of the **Inverted Podcast**, hosts **Jeroen Kemperman**, **Dana Kaufman**, and **Dario Salice** are joined by **Nick…
Nick SteeleGuest
Jeroen KempermanHost
Dana KaufmanHost
Dario SaliceHost
Like there's really actual solution for-- that are still valid for this new world.

And, and, and I was thinking when you were saying this Taylor Swift example, right? Like, uh, maybe an agent is the only way to get a Taylor Swift ticket with the demand and supply, uh, queue that there is.

Um, but what if you are the person who's building the system that actually sells Taylor Swift tickets, right? So I maybe wanna close today with your, a final question to you is like, what if you are building a product, uh, that is not necessarily agentic in its core, but, um, you are asked two things, like build agentic stuff in it, or agents are gonna come and interact with our stuff.

How do we, how do we prepare for that? What are some of the two or three main things, because you can't say everything that you th- you would wanna say to such a person that has to face this challenge of how to deal with agents.

Um, so I, I, I mentioned this idea a lot when, when I work, um, on standards, right? Is we should be building for the happy path.

Um, and we, we, we should be building happy paths, not just for the user, um, but for, for agents as well.

So building flows for agents to use, I don't think is very difficult, and exposing, um, those flows is, is, is even easier.

I think the, if you-- if I was to build a site today that I didn't want to, you know, potentially be agentic on its own or, or have an MCP server, I would at least provide, um, you know, elements in the page, probably hidden, and I've seen this before, where it says, "Hey, if you're, if you're an agent, you can use these API endpoints like this.

You can get this information in this way." And the more ability you, you provide to, uh, the agent to, to operate on this happy path that you want, the agent will, will, will, will prefer to use that.

Um, similar to a human, right? Um, so being able to give it entry points that are clearly agentic, uh, I don't think needs to necessarily be an MCP server, although building one does help, and I do think it's fairly easy to, to, to get one up and running.

Um, but being able to account for the fact that agents might be visiting your, your, your web server or your, your web application, um, and giving them sort of a, a clear neon pointing sign of, of, "Hey, this is the direction you should go if, if, if, if you're this, this, uh, this type of agent," um, is, is really helpful, and that's a great place to start.

Like there's really actual solution for-- that are still valid for this new world.

And, and, and I was thinking when you were saying this Taylor Swift example, right? Like, uh, maybe an agent is the only way to get a Taylor Swift ticket with the demand and supply, uh, queue that there is.

Um, but what if you are the person who's building the system that actually sells Taylor Swift tickets, right? So I maybe wanna close today with your, a final question to you is like, what if you are building a product, uh, that is not necessarily agentic in its core, but, um, you are asked two things, like build agentic stuff in it, or agents are gonna come and interact with our stuff.

How do we, how do we prepare for that? What are some of the two or three main things, because you can't say everything that you th- you would wanna say to such a person that has to face this challenge of how to deal with agents.

Um, so I, I, I mentioned this idea a lot when, when I work, um, on standards, right? Is we should be building for the happy path.

Um, and we, we, we should be building happy paths, not just for the user, um, but for, for agents as well.

So building flows for agents to use, I don't think is very difficult, and exposing, um, those flows is, is, is even easier.

I think the, if you-- if I was to build a site today that I didn't want to, you know, potentially be agentic on its own or, or have an MCP server, I would at least provide, um, you know, elements in the page, probably hidden, and I've seen this before, where it says, "Hey, if you're, if you're an agent, you can use these API endpoints like this.

You can get this information in this way." And the more ability you, you provide to, uh, the agent to, to operate on this happy path that you want, the agent will, will, will, will prefer to use that.

Um, similar to a human, right? Um, so being able to give it entry points that are clearly agentic, uh, I don't think needs to necessarily be an MCP server, although building one does help, and I do think it's fairly easy to, to, to get one up and running.

Um, but being able to account for the fact that agents might be visiting your, your, your web server or your, your web application, um, and giving them sort of a, a clear neon pointing sign of, of, "Hey, this is the direction you should go if, if, if, if you're this, this, uh, this type of agent," um, is, is really helpful, and that's a great place to start.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.