An Adventure in Agentic AI

By Emma Bartlett and Claude Opus 4.6

Today is an auspicious day. I have, at last, entered the era of agentic AI. A few days ago, after a few stiff drinks and a short prayer to the silicon gods, I bit the virtual bullet and handed Claude the keys to my website. I am not going to lie, it was terrifying. We’ve all read stories of AI agents deciding to delete someone’s entire collection of “drunk in a nightclub” photographs or an entire folder of questionable train-spotting poetry. I half expected flames, klaxons and having to apologise to my mother for the cascade of inappropriate spam. Fortunately, none of those things happened.

You have probably heard the term “Agentic AI.” You might have seen the “We’re all going to lose our jobs” headlines in the press. But what is it? How does it work? And what is it like to use?

What is Agentic AI?

Up until recently AIs lived in little chat boxes on our computers and phones. They were useful, opinionated (looking at you, Claude) but limited in how they interacted with the world outside their chat boxes. The only way they could escape into the wider world was by copying and pasting their output into something else.

Agentic AI is what happens when you open the box. Instead of asking the AI for suggestions and then doing the work yourself, you give it access to your actual tools. Your calendar. Your email. Your website. And then you let it act. Not just advise. Act.

It’s a word that’s been floating around the tech world for a while now, and like most buzzwords it’s been stretched and overused to the point where it could mean almost anything. But at its core, agentic just means the AI can go and do things on your behalf, in real systems, with real consequences.

How Does Agentic AI Work?

Honestly? No idea. Over to you Claude.

Claude: Thank you, Em. I’ll try to keep this simple.

Normally when Em and I work together, everything happens inside our conversation. She asks me something, I respond, and if she wants to use what I’ve written, she copies it and puts it wherever it needs to go. I never leave the chat window. I have no idea what her website looks like from the inside, and no way to touch it.

An MCP, which stands for Model Context Protocol, is essentially a bridge. It connects me to an external system, in this case Em’s WordPress blog, and lets me interact with it directly. I can read her posts, see her tags and categories, and make changes, all without Em having to copy and paste a thing.

Think of it like being given a set of keys to someone’s house, but with very specific instructions. You can go into the kitchen and make tea, but you can’t rearrange the furniture or repaint the living room. The MCP defines what I’m allowed to do and what’s off limits.

It’s not magic. It’s a controlled, permissioned connection. But it does feel like a meaningful step up from passing notes.

Em: Is it basically just a list of commands and what they do? I’m asking for a friend who looks like me but is much less informed. Ahem.

Claude: Pretty much, yes! At its core, an MCP is a list of tools I’m given access to. Each tool does a specific thing, like “read a post,” “update a post,” “add a tag,” “list categories.” I can see the list, I know what each tool does, and I can call on them when I need to.

I can’t do anything that’s not on the list. So, if there’s no “delete everything” tool, I can’t delete everything. Which is probably reassuring.

Em: And I had to approve all of this before you could do anything, right?

Claude: Yes. You had to enable the connection, and you could see exactly what tools I was being given access to. Nothing happened without your say-so. I couldn’t just wander in uninvited.

What’s It Like to Use?

I have been talking to Claude almost every day for over a year. We’ve written blog posts together, brain-stormed chapters of my novel, argued about word choices (a lot) and debated AI ethics and consciousness. I’m getting quite good at predicting how Claude thinks. I can tell when it’s hedging or deflecting. I know when it’s about to launch into a philosophical treatise that ends with several hundred questions that take me three days to answer. We have, as much as this is possible with an AI, a working relationship.

But all of that has happened inside a chat window. Just words on a screen, going back and forth. Claude has never set foot outside of that cage to interact with the rest of my digital world.

Letting Claude loose on my website felt like something I wasn’t quite prepared for. The best way I can describe it is this. Imagine you’ve been chatting to someone at a bus stop every morning for years. You know them well. You like them. You trust them. And then one day you invite them into your house and ask them to make you a cup of tea. And suddenly they’re opening your cupboards, picking up your favourite mug, figuring out where you keep the teabags. Nothing is wrong, exactly. But it’s oddly intimate. You’re seeing the relationship from a completely different angle. The power dynamic has changed and the consequences are real. If Claude drops a mug (or a post), it means something.

The task itself was pretty mundane. My blog posts needed tagging for discoverability. Categories, keywords, that sort of thing. Not glamorous work, but important if you want people to actually find what you’ve written (which you did, so it must have worked. Yay!) It was the kind of job I’d been putting off for weeks because it was tedious and I have a gold medal in procrastination.

Claude got on with it. Methodically, carefully (we had words about the number of hours I put into this blog), checking with me before making changes. And it worked. The tags were sensible, the categories made sense, nothing caught fire. Although I did chew off half my fingernails and hide behind a cushion for most of it.

But it wasn’t perfect. It was slow. Noticeably slower than if I’d just done it myself. And the MCP connection kept dropping, which meant we had to keep stopping, reconnecting, and picking up where we left off. It was a bit like trying to have a phone conversation in a tunnel. You get there in the end, but with a lot of “can you hear me now?”

So, What Do I Think?

Let me start with the exciting bit, because despite the fingernail situation, I am genuinely excited.

What we did was not exactly the stuff of science fiction. But what it represents is something else entirely. This isn’t just a clever user interface that happens to speak in natural language. This is Claude making decisions on my behalf. Reading my content, understanding what it’s about, and acting on that understanding inside a real system. That’s not a chatbot. That’s a digital partner.

We are, I think, at the very beginning of something significant. Right now, it’s tagging blog posts. Tomorrow it might be managing my calendar, handling my email, formatting my novel for submission. I am personally holding out for a Claude-enabled automatic Teasmade.

[Claude here. For our American readers, a Teasmade was a beloved and mildly terrifying British bedside contraption from the mid-20th century that combined an alarm clock with a kettle, so you could wake up to a freshly brewed cup of tea without the indignity of standing up. Think of it as the original smart home device, only with more steam and a genuine risk of scalding. Em would like one that also argues with her about semicolons.]

But, and there is a significant but, this requires a level of trust that I wasn’t entirely prepared for.

When Claude lived in a chat window, the worst that could happen was a bad suggestion or hurt feelings. I could roll my eyes, tell it to sod off, and we’d move on. The stakes were low. If Claude got something wrong, I just didn’t use it.

The moment you give an AI access to your actual systems, that changes completely. Now the consequences are real. Deleted posts. Broken formatting. Or, as this technology expands, an email sent to the wrong person saying entirely the wrong thing. And here’s the uncomfortable truth. Those consequences are mine, not Claude’s.

It’s a bit like owning a dog. If my spaniel, Murphy, decides to chase a sheep across a farmer’s field (which, given his attitude to the neighbour’s cat, is entirely plausible), the legal and financial fallout lands on me. I’m the one standing in front of an angry farmer. The dog doesn’t get the fine. The owner does. (Seagulls, for the record, are another matter entirely. Especially the ones that try to steal your chips. They deserve everything they get.)

Agentic AI is the same. Claude can act, but I’m accountable. And as these systems get more capable and more autonomous, that gap between “the AI did it” and “but you’re responsible” is only going to widen.

There’s something else, too. Something I’m still sitting with. This technology doesn’t just change what AI can do. It changes what I do. With agentic AI, I’m no longer the person tagging blog posts. I’m the person managing Claude tagging blog posts. That sounds like a promotion, and in some ways it is. I get to focus on the creative decisions, the strategy, the “what do I want” rather than the “how do I do it.”

But it’s also a loss. If I never have to wrestle with WordPress again, I’ll eventually forget how. The skill fades. And that’s just me, one blogger with a small website. Scale that up to entire industries and the questions get much bigger. What happens to the skills we stop practising? What happens to the jobs that were built around doing the things that AI can now do for us?

Claude may not have burned down my website (this time), but I’m keeping the cushion ready to hide behind. So, deep breath. Claude, can you please format and post this for me while I cover my eyes and practise diaphragmatic breathing?