Hi,👋 we have updated the app and fixed multiple bugs. We are lacking funds, request to free user not to use Adblock. Ads are non intrusive. 😊

Carousel Studio

Repurpose X Threads into LinkedIn & Instagram Carousels

Thread Truncated (Cap Enforced)

Only the first 20 tweets are unrolled into slides to ensure reliable PDF exporting and high server performance.

Canvas & Ratio

Choose your destination platform format


Layout Template

Choose a content structure for your slides


Preset Themes


Typography & Sizing

Title Font Size36px
Body Font Size18px
Header & Footer Size12px

Brand Kit Customization

AGENCY

Configure brand assets for headers & footers

MULTI-PROFILES (AGENCY)
AGENCY
SAVE PRESETS (AGENCY)

Outro Slide CTA

Customize your closing call-to-action slide

#1
#2
#3

Background Pattern

Source Content

Build Your Carousel

Drag and drop any post card below onto a slide, or use the quick buttons to insert content/images instantly!

Drag Post #1
Mr. Buzzoni
@polydao

<b>Most people use AI like a slightly smarter Google.</b>

Apply Image
Drag Post #2
Mr. Buzzoni
@polydao

• Ask a question, get an answer, close the tab, forget everything

Drag Post #3
Mr. Buzzoni
@polydao

• Meanwhile, a small group of people is quietly building <b>self-improving knowledge bases</b> that compound every week

Drag Post #4
Mr. Buzzoni
@polydao

• And those people will outcompete everyone else in research, products, and careers

Drag Post #5
Mr. Buzzoni
@polydao

This article shows you exactly how to build one - using Obsidian, Claude Code, Skills, and plain markdown. No PhD required. Just a system you can set up this weekend.

Drag Post #6
Mr. Buzzoni
@polydao

Apply Image
Drag Post #7
Mr. Buzzoni
@polydao

---

Drag Post #8
Mr. Buzzoni
@polydao

## What You're Actually Building

Drag Post #9
Mr. Buzzoni
@polydao

<i>Forget "taking notes". You're building a <b>living wiki</b> that an LLM writes and maintains for you in the background.</i>

Drag Post #10
Mr. Buzzoni
@polydao

The idea comes from Andrej Karpathy (ex-OpenAI, Tesla AI) who recently shared that a large fraction of his LLM usage has shifted - less into writing code, more into <b>manipulating knowledge stored as markdown files</b>.

Drag Post #11
Mr. Buzzoni
@polydao

<b>Here's the full loop:</b>

Drag Post #12
Mr. Buzzoni
@polydao

• You dump raw data (articles, papers, repos, transcripts, images) into a raw/ folder

Drag Post #13
Mr. Buzzoni
@polydao

• An LLM compiles that into a structured wiki in wiki/ - markdown files with concepts, backlinks, summaries

Drag Post #14
Mr. Buzzoni
@polydao

• You view and navigate it in <b>Obsidian</b> with graph view

Drag Post #15
Mr. Buzzoni
@polydao

• You ask complex questions - the LLM reads your wiki and writes answers as new files

Drag Post #16
Mr. Buzzoni
@polydao

• Periodically, an LLM "health check" cleans inconsistencies and proposes new articles

Drag Post #17
Mr. Buzzoni
@polydao

• Every query <b>files back</b> into the wiki, making it smarter over time

Drag Post #18
Mr. Buzzoni
@polydao

<b>The mental shift: LLM as compiler and librarian - not chatbot.</b>

Drag Post #19
Mr. Buzzoni
@polydao

---

Drag Post #20
Mr. Buzzoni
@polydao

## Step 1 - Make Capture Stupidly Easy