Ask most AI chatbots to build you a custom chatbot and you'll have to leave the chat window or jump into a seperate builder interface. But, if you ask Claude, it just does it — live, in the same browser window, in about ten seconds.
This is the remarkable trick behind what Anthropic calls Artifacts with nested API calls — known among power users as “Claude in Claude.” It’s one of the rare AI features that actually feels new, and most people have no idea it exists.
What exactly is 'Claude in Claude'?
When Claude creates an Artifact — the interactive app or document that appears in a side panel on Claude.ai — that app can itself make live calls to Claude's API. In other words, the mini-app Claude builds for you has its own AI brain running inside it.
The result is a fully functional, AI-powered application — built by AI, running inside an AI chat interface — that you can interact with immediately, without ever leaving the conversation.
To see it in action, I asked Claude to build a "Hype Man" chatbot — an AI persona programmed to respond to absolutely everything with maximum, unhinged enthusiasm.
Within seconds, a fully functional chat interface appeared in the side panel. So if I typed something like "I made toast this morning." The Hype Man replied: "BRO. TOAST?! YOU ARE LITERALLY BUILT DIFFERENT. THE WAY YOU OPERATE THAT TOASTER IS ELITE BEHAVIOR."
Absurd, sure. Geniunely impressive? Absolutely!
Why this is a bigger deal than it sounds
Building an AI-powered application normally requires meaningful technical skill: you need API keys, a development environment, a working knowledge of how to structure API calls, a frontend to display results and somewhere to host the whole thing. Even for skilled developers, it's at minimum an hour of setup. For non-developers, it's effectively impossible.
Claude collapses all of that into a single conversation. You describe what you want, and within seconds you have a working prototype you can actually use — and share with anyone who has the link.
Like any AI, the feature has limits worth knowing. The mini-apps Claude builds are ephemeral by default — they exist in your session. That means, if you want to use it again, you'll have to be sure Claude's memory is enabled so it can retrieve it again.
Also, something to note is that each conversation the inner AI has also costs API tokens, so heavy usage of a complex embedded chatbot can add up if you're on a paid API plan. For casual use within Claude.ai's interface, this isn't a concern — but it's worth understanding the architecture.
How to try it yourself
You don't need to do anything special to access this feature — it's built into Claude.ai and available on all plan tiers. Just start with an open chat window.
The most direct approach: tell Claude you want to build an AI-powered app, then describe the persona or purpose. Try something like: "Build me a chatbot that acts like a skeptical editor reviewing my writing" or "Create an AI assistant that only speaks in the style of a 1920s detective." Let your imagination go wild and Claude will handle the rest — writing the code, embedding the API calls and rendering the finished app in the side panel.
You can also iterate in real time. For example, if you don't like the personality, just tell Claude to adjust it. Want to add a feature? Ask. The app updates instantly.
Bottom line
The AI chatbot space is crowded and the feature sets are converging fast. Most things Claude can do, ChatGPT or Gemini can do something similar. But this particular combination — describe a custom AI persona, get a working AI-powered app in seconds, no code required — is genuinely Claude's own territory right now.
My guess is it won't stay exclusive forever. But for now, if you've ever wanted a custom AI assistant tailored to exactly your needs without touching a line of code, Claude is the place to build it. Give it a try and let me know what you think in the comments.
Follow Tom's Guide on Google News and add us as a preferred source to get our up-to-date news, analysis, and reviews in your feeds.
