🤖 WeWeb AI planning, task tracking, and MCP improvements

Announcements New Releases
1

Hey everyone :waving_hand:

This release brings clearer planning and task tracking to WeWeb AI + MCP support improvements!

Check out the details :backhand_index_pointing_down:

:page_facing_up: Clearer planning and task tracking in WeWeb AI

Follow progress with task tracking

WeWeb AI now shows a task list while working on larger requests, making it easier to understand what it is doing and how far along it is.

You will see a progress card showing the tasks it plans to complete, how many are done, and which ones are still in progress:

This helps you:

  • Understand the steps behind a larger request
  • See progress without waiting for the final result
  • Quickly spot what has already been completed

Improved planning

Plans are now clearer, more structured, and easier to review in a dedicated Plan mode:

A plan now includes:

  • A summary of what WeWeb AI intends to do
  • Technical details for the proposed implementation
  • A clearer overview of what may be created or updated in your app

After reviewing the plan, you can approve it or continue chatting to refine it.

Once approved, WeWeb AI switches to Build mode and uses the approved plan as context to complete the work.

Other WeWeb AI improvements and fixes

WeWeb AI now better follows best practices and respects your existing project setup.

This includes improvements to:

  • Using, creating, and updating design system tokens more reliably
  • Reusing existing sections when relevant
  • Choosing native WeWeb components instead of recreating them from scratch
  • Respecting existing icon libraries
  • Handling hover and active states more consistently
  • Applying styling choices more predictably, including colors and existing element styles
  • Setting the app’s default theme when the app design is light or dark
  • Generating cleaner, more beginner-friendly JavaScript with helpful comments

:linked_paperclips: MCP improvements

The team made a series of improvements to MCP support, including:

  • MCP sessions no longer drop
  • MCP now uses tokens from design system by default
  • MCP now setups debounce by default when building inputs
  • Fixed issues that could happen when creating dynamic links
  • MCP now uses the native WeWeb Calendar element by default
  • MCP now leverages reusable sections when building multi-page apps
  • MCP now properly uses the hover state instead of adding state logic through a workflow
  • Fixed issues where MCP was struggling with API endpoints related to tables using paramaters
  • Improved readability of MCP outputs in workflows with instructions to write more beginner-friendly JS code and comments

That’s all for now! As always, let us know what you think :slightly_smiling_face:

2

Hey there,

Thanks for the updates! Just wanted to drop some quick feedback regarding the recent WeWeb AI changes. Right now, tokens are burning like nowhere before. Guess it is because of extended Planning and Reasoning of the agent (which did not lead to better results at all). I have the feeling that it is trying and thinking “too much” now.

To give you some context, here is what I just ran through:

  • Adding skeleton loaders to a dashboard: 3 Million tokens

  • Adding some process steps: 2 Million tokens

  • Trying to add a simple submenu to a sidebar item (2 items): 3 Million tokens.

That last one was especially rough—after a few fixes, the last iteration broke everything. I had to roll back to a backup because the option to revert/circle back wasn’t available.

That is 8 Million tokens in total, and I wasn’t even asking it to create whole sections, complex workflows, or entire pages. We are talking about relatively simple UI tweaks.

At this rate, my plan (€25 for 10M tokens) is going to evaporate instantly. I honestly feel like pulling in Claude Fable 5 would even be cheaper at this point. In my opinion, the previous version felt much better and more efficient.

I think I’m going to have to look into trying MCP for now. Anyone else noticing a massive spike in token consumption for minor edits?

3

Hey Michael, thanks for taking the time to provide detailed feedback. It’s super helpful! I’ll pass it on to the team. Would you mind creating a feedback ticket here if you haven’t already with a link to your projects so the team can take a look and investigate further? I’m not sure if it’s a new release thing or something else going on but definitely worth a look on our side.

4

Hey again!

Quick update on this:

We indeed had an issue post release where we weren’t counting tokens properly. This has been fixed and miscounted tokens were added back to the workspace :slight_smile: