Have your AI agent read your chats with them daily and turn your feedback into rules.
Personal rules go in its memory. Project rules go in AGENTS.md, so your whole team's agents learn them.
We’re testing 4 ways to show Packs on profiles.
Which one do you prefer? Vote 1–4 👇
1. Pack rows
https://t.co/zFejppRKnA
2. Packs tab
https://t.co/1Ot1kTlp9B
3. Pack cards
https://t.co/OThmM3pS4d
4. Open rows
https://t.co/DNnnuMHY5Y
Screenshots are attached in the thread.
My new morning routine: an AI agent reads user feedback and turns it into problem statements, each mapped to an NN/g heuristic.
If the fix is frontend-only, another agent forks our latest prototype, builds 10 options and opens a PR.
I still make the calls. I just start from options instead of a blank page.
Creative direction shouldn’t be picked by asking, “Do we like how this looks?”
Ask: Does it say the right thing, to the right people, in the right way?
Brand strategy defines who we’re speaking to and what we want them to understand.
Creative strategy defines how we express it.
We’re testing 4 ways to show Packs on profiles.
Which one do you prefer? Vote 1–4 👇
1. Pack rows
https://t.co/zFejppRKnA
2. Packs tab
https://t.co/1Ot1kTlp9B
3. Pack cards
https://t.co/OThmM3pS4d
4. Open rows
https://t.co/DNnnuMHY5Y
Screenshots are attached in the thread.
When you're building a feature with common patterns: editing a profile, changing an avatar, or connecting an MCP to a chat, try using Mobbin MCP: https://t.co/ESCVRQBscC
Ask your AI tool to find examples through Mobbin, spot what they have in common, and use them to build a first version.
Minimal input from you, and you’ve already got something to work with.
The best part is that you don’t have to reinvent what the industry has spent years refining. Start where others left off, then make it better.
For example, I’m new to building for AI tools, and just by going through this exercise, I discovered that:
1. An MCP can be connected to a specific chat, an entire project, or your whole profile.
2. MCPs can be predefined and installed with just a URL.
3. You can enable or disable specific MCP tools.
4. The connection flow can include states like Error and Retry.
4. An MCP connection can have its own UI as part of the model’s response.
Limitless @lmtless_esports joins NAVI as our official prediction market partner and our fans just got a home.
Markets built by esports fans, positions traded peer-to-peer, outcomes called by the community.
NAVI doesn't play it safe. Neither does Limitless.
User-Generated Markets are LIVE on Limitless
We’re fundamentally reshaping how users interact with prediction markets:
1. Pick an asset
2. Choose an outcome
3. Launch a market
Every creator earns a fee share from its trading activity
Create yours → https://t.co/qYwZiXHCcD
$LMTS Season 3 Airdrop Claim is LIVE
Season 3 was our biggest one ever, and it’s getting our biggest airdrop ever
To match a record-breaking season, we’ve allocated 3% of the total $LMTS supply to reward our traders
Claim here → https://t.co/iA1jixNx4J