🎉 Introducing AutoBubble — Build and ship Bubble plugins with AI

[hobum91]

additional feedback is here~!

• My plan is remained unsubscribedafter subscribing starter plan.
• There’s no log out button and I see sign out button in the setting tab.

I’m waiting to built with autobubble. Please check the issues. Thank you carlovsk.

[carlovsk.edits]

Hey! Thanks for the heads up, and sorry for the friction.

Honest confession: I’ve been so obsessed with making AutoBubble actually ship good plugins that I kinda left Stripe alone in a corner. It got jealous, started a race condition, and locked a couple of users (including you ) on the ‘trial’ plan even after paying. Drama. Fixed now.

Your account is now active on the starter plan.

On the sign out: it does exist today under Settings → Sign out, but you’re right that it should be in a more obvious spot (header / account menu). Adding it to the list.

Thanks for being patient and for the feedback, genuinely helps. Excited to see what you build!

[hobum91]

It seems there’s a bug where, when running multiple chats simultaneously, the Agent reflects the results into other plugins. It appears the Agent is not executing in parallel.

Specifically, I created four plugins and am chatting with the Agent in each, but the results from chat A are being applied to plugin B. This ended up overwriting existing work. Even the titles ended up being synchronized..!

I like Autobubble but this should be fixed ASAP..!

[carlovsk.edits]

Hey!

Thank you so much for all the feedback, you have no idea how much it helps me. I can’t test all the scenarios, and this public beta has been great thanks to your feedback.

I’m already fixing it and I’ll be back with updates later!

[hobum91]

I would really appreciate it if you could also look into the following:

• When the Claude API usage is exhausted and I switch the AI provider to Autobubble, it fails to recognize the existing conversation and does not return responses. (This not only degrades the user experience but also causes financial loss, as only Autobubble credits are consumed.)
• It would be more useful to have separate plan mode and build mode like buildprint.ai. (This could help prevent unnecessary credit usage.)
• In addition to the Claude API, it would be great if Claude Pro or Max could be supported. Since the Claude API uses a completely separate billing system, as a Claude Max user, I end up paying twice. This becomes an unnecessary barrier for Autobubble users.

[hobum91]

The reason I am confident in Autobubble’s success is that it enabled me to quickly and easily develop two highly useful plugins.

1. The first is a plugin that accepts any type of field (including option sets), performs arithmetic operations such as A+B+C/D*2, and returns the calculated result.

2. The second is a plugin that interacts with a Vimeo player embedded via an HTML element. By simply providing the element’s id attribute, it can return playback time, total duration, and play status in real time—without relying on “do when condition is true” events or “run JavaScript” actions.

I was able to build both of these in just one day because they address problems I had long wanted to solve more efficiently. In other words, these were features that made me think, “I chose Bubble to build things quickly and easily, but implementing this within Bubble is unnecessarily cumbersome—how can I simplify it?”

For Bubblers like myself who don’t have coding experience but still want to solve practical problems, this tool is extremely valuable.

[carlovsk.edits]

Thanks for the detailed feedback, this is exactly the kind of input
that shapes the roadmap. Quick reactions to each point:

@hobum91

When the Claude API usage is exhausted and I switch the AI provider to Autobubble, it fails to recognize the existing conversation and does not return responses. (This not only degrades the user experience but also causes financial loss, as only Autobubble credits are consumed.)

Highest priority for me. Two fixes coming:

1. Existing conversations will keep working after switching providers,
   right now they get stuck because the thread is tied to the original
   provider, that is being fixed.
2. Failed or empty responses will not deduct credits, so this kind of
   issue never costs you anything while it is being resolved.

@hobum91

It would be more useful to have separate plan mode and build mode like buildprint.ai. (This could help prevent unnecessary credit usage.)

Agreed, Plan Mode is on the roadmap. The idea is to let you scope and
validate the approach with a lighter model before committing credits
to the actual build step.

@hobum91

In addition to the Claude API, it would be great if Claude Pro or Max could be supported. Since the Claude API uses a completely separate billing system, as a Claude Max user, I end up paying twice. This becomes an unnecessary barrier for Autobubble users.

Also on the roadmap. Looking at OAuth-based integration with the
Claude subscription so Max users can plug their own account in and
skip the double billing.

[carlovsk.edits]

Hey everyone

A few updates were released earlier this week:

Connect with your Claude account (no API key needed) You can now sign in with your Claude Pro or Max subscription directly, no need to generate an API key or manage billing on the Anthropic side. If you already pay for Claude, you can just plug your account into AutoBubble and go. API key support is still there for anyone who prefers it.

No credits charged on failed requests If a generation fails or the AI doesn’t return a valid patch, you won’t be charged credits anymore. Only successful edits consume credits.

Bug fixes A handful of fixes around chat isolation per plugin and the AI provider picker, plus smaller polish across the editor.

What’s next: Plan Mode The next feature I’m shipping is Plan Mode, where you can work with the AI to draft a plan first, review and adjust it, and then have it implemented in your plugin. Should make bigger changes a lot more predictable.

As always, feedback is very welcome, I’m right here in the thread.