Sandboxes have no moat. Just fat margins. We're launching agent37.com to kill those margins. For example, a sandbox with 2 vCPUs and 4 GB RAM when left running for an entire month: Vercel: $249 Cloudflare: $145 Daytona: $121 Agent37: $4.76 There's nothing magical about a sandbox that justifies keeping it expensive forever. Call it a race to the bottom. We'll see you there. If you can find a cheaper sandbox and we'll refund the difference.

Since we're being nitpicky in community notes. Even at 6% CPU utilization which was their average usage, Vercel sandboxes are 15× more expensive than Agent37. And at 10,000 instances, that a $731,000 bill with vercel vs $47,600 with agent37. If you're looking to scale agents and needs sandboxes, Agent37 is a no-brainer. nitter.siddz.com/an_engineer_log/status…

Today, the @lettercompany is releasing the beta of Letterpress-1, the world’s first coding agent, harness, and IDE purpose-built for growth engineering. tl;dr: check out the 🧵 to see the product in action. Growth is re-emerging as an engineering problem, but today’s coding tools weren’t designed for it. Your website isn’t isolated like your app: it reacts to the outside world (e.g. agent behavior, Google rankings, observed human interactions, and competitor activity). Leading coding agents were built to scale complex codebases, not to autonomously build for outside signals. Letterpress-1 is. Letterpress-1 is designed to tackle growth problems of every size. It’s also proactive: it suggests the nth next thing to build for growth. It'll issue pull requests for de-anonymization, experimental landing pages, warmed emails, blog automations, agent telemetry, etc. The Letterpress IDE is also built into your site. Press ⌘+L, authenticate, and edit text directly on your website. Letterpress-1 automatically opens a pull request with the change. Letterpress-1 ships with readily available infrastructure to stage futuristic growth strategies that win over agents. These include: => Proofs: autonomous evidence chains that verify customer success data for agent visitors => Simulations: staged mirror applications where agents can safely try solutions before buying => Benches: self-hosted, reproducible benchmarks with open-source, independent governance => Phantoms: autonomous websites to sandbox growth strategies Build, automate, and refine your growth process with the Letterpress family of tools. We're proud to count some of the world's most forward-thinking startups as our customers. Sign up today at letter.dev. I’ll share a few examples of Letterpress-1 in action in the thread below.

So @tjlfit has taken up a challenge to get me 6 packed in 6 months 🤣 Let's see how this goes..

AI has made it easier for me to waste time and feel productive doing it. I sometimes have five or seven Claude Code sessions running. Things are getting built. I feel like I’m flying. Then I stop and ask which of these actually moves the needle. Maybe one. The rest is low-priority bullshit I picked up because it was easy to start. It’s getting a fraction of my attention while I supervise everything else. When building something took real effort, I was ruthless about choosing what deserved doing. The cost forced me to prioritize. Now starting six extra tasks feels almost free. But checking their work, answering their questions, and switching between them still takes my attention. I think I’m sometimes finishing more tasks while making the thing that matters take longer. That’s the illusion of productivity.. Before I open another session, I need to ask: If I could only get one thing done today, would this be it?

gemini is about to steam roll the competition.. they're just getting started on post training the beast.

hahaha, been there! It's the reason we don't have a free plan on agent37 sandboxes :(

One of our customer David Oralevich used to buy a Mac mini for every client who wanted an AI agent. Now his agents run on Agent37, for law firms, doctors, property manager and college students. "There was one point where I had a stack of Mac minis in my office. That's when I was like, I can't.."

throw a rock in SF you'll hit 50 sandbox providers 🤣

introducing Mirrors 🪞 find the mistakes your AI agent keeps making and fix them in real time. spot what keeps going wrong, write the fix once, preview where it lands, and measure if it helped. no more "just add one more line to the prompt."

90 Days of YC: Week 7 2022. I'm in Mexico on a temporary visa, working 16 hours a day. Startup attempt 9 out of 13. My savings were mostly in stocks. Russia invades Ukraine, the market drops, and my bank savings look bleak. I kept telling myself I could take more pain. I could, for a few months.

So cool taan.ai is literally building vibe-coding for music !

they call me unc 😭

SF founders, if you’re building agents, come grab dinner with us tomorrow. @EagleTong3 and I are getting 15 founders together. We have some fun activity with dinner as well :) 7pm. 3 seats left luma.com/kupz9ie8

I have a surprise for my intern, she was asking for a chair last week.. And I found this beauty in the garage !

did gemini just cook ?

We just launched TrueMile (@ycombinator F26), an AI-native trucking company. Our AI plans loads, finds freight, negotiates with brokers and dispatches drivers. When it picked our loads, we earned 17% more per mile than the market.

I got into YC with an insight that was wrong.. but that's ok.. have one anyway in your application. Teach the partners something.

i have been in a few meetings like this in my 15 yr career 🤣