still love an idea of generative ui, still want to build smth around this. think this may melt brains of llms a bit, but def cool
OpenUI now renders within @assistantui
Your agent can now generate interfaces or take structured input via real forms - all inside the most loved Agent UI framework. @KashyapVisharad cooked with this one!
assistant-ui.com/docs/tools/…
I enjoy idea of dynamically generated UI for interactions with AI agents, curious what guys from monogram.ai will build
Looking for inspiration on what AI Agent as a product UX/UI shall look like.
I think these days everybody ends up stealing from frontier companies like: Cursor/Codex app/Claude app/Devin/Cofounder co/Perplexity
They look good but I feel there's soo much ahead
Could be an alternative to obsidian for managing agents knowledge base/skills(?)
Introducing @OpenKnowledge, the best markdown IDE for humans and agents.
Open source. Local and private. LLM-wiki ready.
Use with Claude, Codex, and your favorite agent today.
Aleksei Naumov retweeted
New skill: /apple-design
Apple’s WWDC videos are a goldmine of knowledge. I’ve combed through my favorite ones and came up with 17 design and motion principles.
Use them to review existing work or when working on something new to get it right.
github.com/emilkowalski/skil…
Aleksei Naumov retweeted
How to save 50% of claude code/codex usage:
In claude code have you seen messages like "231k uncached tokens" in the bottom right corner?
This happens if you reply in a conversation more than 1h old. And if you do those [???]k tokens would be deducted from your usage limit (which can be substantial if it's e.g. 500k fable5 on pro subscription)
You can save it by (1)noticing when you're almost at the session limit (2)asking to loop sleeps before your session reset time and resume normal task work after that
Works like a charm
Last 2 month I’ve been working on building anrie.ai
AI performance marketer that lives in your slack. If you have no idea how to run meta ads definitely check it out, free creds incl.
So bullish about the future of personal and business agents
it's time to change the scope of my X, as for last 4 months I've been working not only on Gen AI but mostly on building agentic systems that help people to run Meta ads.
Meanwhile check out the product that I've been working on for last month: anrie.ai/
We won $10k GPU with this project on a hackathon by @bfl_ml and @aiengine_hack last week, here is our workflow:
1. You upload a floor plan -> generating top-down and side views of furnished and decorated flat w/ nano banana.
2. Based on this 3D model is generated (Trellis on @fal)
3. Using top down and side view we generate 360 equirectangular images using nano banana -> embed them using panellum.js
4. Room editing with a prompt: FLUX-2 Pro or Nano banana.
That's only a part of a stack though, lot's of tricky heuristics hiding underneath!
Luma Ray 3.14 just dropped by @LumaLabsAI and I compared it with Ray 3, released earlier this month - the quality jump is INSANE!
Workflow tip: edit videos straight with a prompt.
Check examples + prompts:
Visited @veedstudio office today — met @sab8a and Aleksei, was super excited to meet the team behind VEED Fabric!
Talked about the future of agentic video editing, avatar model improvements, and ways to level up the product even more. Looking forward to more collabs! 🚀



























