We're still early.
But the direction is clear:
Give information a visual workspace.
We're building DrawsyAI for developers, teams, and anyone who needs to understand complexity and turn it into something they can work with.
🚀 The DrawsyAI pool is now LIVE on @CyreneAI
🏊 Pool:
0x03Cbf6b56d9e432733288Ad003F639Eb1264C485
🔗 cyreneai.com/projects/drawsy…
Replying to @spakhm
There’s a lot of nuance here. We tried turning the whole thing into a visual system the context, sequence, and failure modes are much easier to see this way made with drawsyai.tech
We gave Drawsy one system design question:
“Design a news feed system.”
Requirements:
- mobile app as well as web app
- user can publish a post and see friends posts on news feed page
- feed is sorted by reverse chronological order
- User has 5000 friends
- traffic volume is 10 million DAU
- feed can contain media files including both images and videos Can you propose a High-Level Design (HLD) for this news feed system?
It gave us this.
API → feed service → event bus → fanout → Redis → DB → read path → media pipeline.
The fun part starts now:
Can we challenge the architecture, change it, and keep the reasoning on the same canvas?
drawsyai.tech
How would you design a payment platform handling 10M+ transactions/day?
We sketched a first-pass architecture in DrawsyAI covering:
• idempotency
• payment ledger
• PSP failures
• event streams
• retries + deduplication
• webhooks
• DLQ / replay
• fraud decisioning
What would you change before production?
Most AI coding tools optimize for generating code.
We’re exploring a different bottleneck: context.
Architecture, decisions, docs, dependencies & code need to stay connected.
That’s the idea behind DrawsyAI an AI workspace for canvas + context + code.
Early days. Building in public. 🚀
#AI #DevTools #BuildInPublic #DrawsyAI #3DShapes #CanvasTools






