Updates to the Jadebook Platform.

When we first built Jadebook, we built it in a monolith-structure where everything was in one place. While this worked great, the scope of Jadebook has increased — where we want to support different platforms. The previous architecture made this extremely difficult so we completely reworked it.

Here's what's been shipped:

1. Flat 20-30% performance improvement
2. Increased backend security and reliability
3. Memory is now much faster to generate and more reliable
4. Major UI overhaul to make everything less janky and far more versatile
5. The editor is now simpler due to our plans to build a mobile app

Oh and we made the marketing site way better :)

We plan on launching on Monday, 2nd June. As such, we've shipped a bunch of updates including many platform bug fixes.

• Use Gemini 2.5 Flash over Gemini 2.0 Flash
  • We've disabled thinking output but in general, 2.5 Flash is faster, more reliable, has more knowledge and has more capabilities
• Allow users to include images and PDFs to their chats
• Updated some document layouts to work more intuitively
• Separate journals
  • We now have the home view which shows all entries from all types of journals.
  • Journals now have a separate section in the sidebar
• Update all empty states to be more friendly to new users
• Add voice transcription (BETA)
  • Free users can use real-time browser transcription if supported
  • Pro users can record in 10-minute sessions and have the OpenAI Whisper model generate the transcription. This will also add grammar and is way more accurate
• Update Memory structure to be more reliable for models to generate — also added goals and aspirations and Values to the schema
• Updated the model used for Memory
  • Previously, generation took take up to 15 seconds. It should now take ~1 second with ~5 seconds being the slow end
• Allow new users to quickly go through an onboarding process, setting their desired theme, username, and layout
• Create onboarding document — shows new user's the rich-text capabilities and AI features
• Add the final background functions for handling automatic document deletions (for entries that have been deleted for over 30 days)
• A metric ton of bug fixes

It’s been a while but there have been a lot of changes made to improve Jadebook. You’ll notice that we removed optional encryption and full-text search. A goal we currently have is to reduce complexity especially when it’s unnecessary and these just happened to be a part of that.

• Guided Journals have been updated to include all the features from the other types of journalling
  • This includes AI features, covers, icons, searching, and more.
• Optional encryption is no longer a thing. Everything will be encrypted always.
  • This also means that full-text search will no longer work. Semantic Search is now the only way the search works
• Added a space under the typing cursor so the text doesn’t hit the bottom of the viewport
• Update Entry UI to be much cleaner and intuitive
  • This includes the icon selector, top bar and now the UI will also fade away when typing to allow you to focus more
  • The quick actions like add icon, add cover and the document date now fade away unless you hover over near them
• We’ve also removed some rich-text features. Thinking about the mobile app, these features would have made development far more difficult for no reason.
  • This include the text-align, subscript and superscript
• Major Goals rework
  • Covers are now supported
  • The Logs editor is wayyy better
  • Logs have an updated rating system. Rather than a thumbs up and thumbs down, we now have on track, off track, neutral and major update
  • Logs now load differently. We load the first 5 and then load more as you scroll. Previously there was so much text and data that it would be overwhelming
• Slight update to how Guided Systems work — mainly performance improvements
• Assets settings rework
  • Assets should now load faster
  • UI has been updated to be more intuitive
  • You can now see what entity the asset is linked to and go to it
    • Eg. If the asset is in a journal entry, you can go to that entry

A core item on our roadmap was a page where user’s can see all their assets and delete them if they want. We’ve finally added it. It’s currently available in the settings and shows file name, file size, date uploaded and let’s you delete the asset.

It should be reminded that Jadebook should not be used as a long-term storage solution. Assets are compressed on upload and we keep these files private, eg, we generate a public url that lasts maybe an hour and then expires. You should probably use something else for file storage.

Summaries

Another feature we’ve added is AI Summaries. When you memorise a journal entry, the AI will now generate a quick summary for you.

AI Chat

The AI Chat now has access to retrieve recent entries. Eg, let’s say you had a great day, well, now the AI knows that and might congratulate you.

By default, the AI Chat will only have access to memorized entries. This is because the AI features are opt-in and the user has control over that they want to share. However, having to memorise all your entries every time seems a little annoying so there is now a toggle in the settings allowing the AI to have access to all entries.

We’ve been focusing on performance and UI. The focus this time was the notes and goals which were previously stored within their parents. I.e the notes were stored within the entry. But this meant we had to add aggressive restrictions as to not take up too much space in a single object.

But with the new Reflective Agents the previous character limit of 600 simply wasn’t enough. So with the new updates, you can now store more notes, the character limits have been increased to 2000 (1000 for free users) and entries in general should be much faster.

• Update Notes and Goals
  • More performance and higher character limits
• New settings sidebar

We’re overhauling the UI a bit to make the newer features fit in better and overall make Jadebook a better experience.

• Updated Home view
• Add drafts (empty entries are shown as drafts)
• Add Recommended Prompts (AI prompts based on your memory) (Pro Feature)
• Minor UI Changes (eg headings are 1 size smaller)