Leibel Hecht

30 Day Challenge starts tomorrow #downloadReco Can you help us get to 500 downloads in 30 days? What is your number 1 growth hack for growing mobile apps?

@ericzakariasson Finally

you need to be tilemaxxing your agents

Grill it!

@simonbs meant Pushover...

@simonbs Been using Pushed ver for a while. Would love to try this

I’ve been working on something… and it’s now on the App Store! 👀 Introducing brrr 🚀 Push notifications to your own devices. Instantly. No signup. No dashboard. No nonsense. Link in 🧵

@kr0der Wait, how do you get that UI?

dude Cursor sucks you can't run multiple agent chats at once!!! Cursor:

@patloeber @GoogleAIStudio What are the rate limits like?

Introducing Gemini Embedding 2! Our first multimodal embedding model for text, images, audio, video, and PDFs. Here's an app you can try in @GoogleAIStudio where you can see multimodal search in action:

@OfficialLoganK Yes!! What are rate limits like?

Say hello to Gemini Embedding 2, our new SOTA multimodal model that lets your bring text, images, video, audio, and docs into the same embedding space! 👀

@elie2222 I have one that triggers post deployment. It waits 5 minutes that analyzes the logs and new db records and sends a health update to a slack channel

@SenorTzvi @RobinhoodApp Sign up bonus?

For all you credit card nerds. @RobinhoodApp just released their own platinum card. Real platinum-plated, $695/yr (incl. Gold), $3K+ value! 🚀 Perks: •5% back dining/flights •10% hotels/cars Credits: $300 travel $500 hotel $469 Priority Pass, $120 TSA/Global Entry $250 autonomous rides $250 restaurant $370 DoorDash $70 Oura $200 wearables $365 Function Health $199 Amazon One Medical Thoughts?

@deedydas How much are the COGS of Cursors model providers vs Anthropic in house?

Narrative violation. Cursor goes $1B to $2B in 3mos. Claude Code went $0 to $2.5B in 8mos. Everyone in the tech/X bubble think people are wholesale ditching Cursor, but enterprise diffusion is glacial. Most of the world just got a hold of it.

@leerob @claytthebuilder @cursor_ai I’m loving cloud agents from slack! Have my mcps connected

@claytthebuilder @cursor_ai I kick off agents from Slack for almost all PRs that I expect to quickly merge and that can be trivially validated. So helpful

I'm liking the feel of Cursor cloud agents for making changes from my phone. I've tried: - termius > Claude code - openclaw These worked well, but cursor agents feels more seamless in my workflow. Current workflow: - Message @cursor_ai in Slack "Make xyz change in this repo" - Cursor spins up agent, creates new branch, completes work and messages back to the thread that it's done. - Agent Creates PR - I review PR, check preview deployment - Tell agent to merge to main - Auto deploys to prod..

@LandseerEnga Would love to try it! Mobile app testing is a bottleneck for us right now

Agents can one shot mobile apps, but testing is still the bottleneck. So we built a CLI that gives Claude Code the one thing it was missing - eyes and hands The best part? t's fully vision-based: - No scripts, no selectors, no element IDs - It interacts with the app exactly like a human would Claude now writes code → tests it on the app → sees what broke → fixes it Spawn a cloud agent, go to sleep, and wake up knowing it actually worked.

@leerob found it. Thanks! Just need to figure out how to set up the secrets #mcp-tools" target="_blank" rel="nofollow noopener">cursor.com/docs/cloud-age…

@leerob I can’t find how to set it up in the docs. Any thing you can point me to? 🙏

Cursor just got a major upgrade! Agents can onboard to your codebase, use a cloud computer to make changes, and send you a video demo of their finished work. The latency of using the remote desktop is smooooth.

@cursor_ai how can I enable my MCP server to be used in Cloud Agents? @leerob @benln any ideas? Thanks!

Why is @github search this bad?

@Austen Following…

Who has figured out the ideal UX to work with OpenClaw agents on dozens of things simultaneously without having them trip over themselves? I don't care for Kanban style. I imagine a giant multi-column layout where each column is an ongoing thread with its own context

@SimonHoiberg @openclaw Do you deploy multiple agents on one machine? How to split up the memory?

Even though the biggest LLMs now have context sizes in the millions, they still get more stupid the more context they have to carry. So the easiest way to make your @openclaw setup much stronger is to simply create multiple agents with each their own expertise. This splits up the memory/tools scopes, and each becomes significantly better. I have a whole team of AI agents in a private Discord. They have their own designated role/responsibility, and they can exchange information with each other when needed.

@UtahRabbi ?

WHAT JUST HAPPENED