Today we are launching Base Code. we’re taking an opinionated approach to building software (prediction, this is the next wave of software tools) For years, getting started meant getting infrastructure and assembling your own version of everything around it. How do we run this locally? How do we set up the cloud environment? Spin up the databases? Give everyone on the team a working setup? Your tools are infrastructure for creating your dev team and infra - now figure it out by yourself. Every team answers the same questions, builds its own glue, and keeps maintaining it. I think that era is coming to an end. You should be able to bring your code and get a working environment, with those decisions already handled. The app, the services, the databases, the preview - all running together. That’s the bet behind Base Code by @Base44. We take an opinionated path from your repo to a working cloud environment, so you can spend your time building the product. And what excites me most is what that unlocks for the team. Share your work. Jump into someone’s branch. Try an idea together. Bring in someone who doesn’t spend their whole day writing code, without asking them to spend their afternoon setting up a development environment. Batteries included should mean freedom to work on what's most important to you and everyone else in the team. I’d love to hear what you think: app.base44.com/base-code

Triggers vs schedules: why polling every ten minutes backfires The most common thing I see in a new Superagent by @Base44 setup is a schedule that runs every ten minutes. Check my email every ten minutes, check the repo every ten minutes. It runs, which is not the same as working. It runs six times an hour to find out that nothing happened, and every one of those runs spends message credits. The cost is the smaller problem. If the connected service starts rate limiting you, runs stop finishing and start queueing behind each other, so the thing you wanted at 9:04 arrives at 9:40 with the backlog behind it. Use a schedule when the work actually belongs to a clock. A morning brief, or a report that goes out every Monday. Anything that should happen because something happened belongs on a trigger. Triggers fire when your data changes or when there is activity in a connected tool, so the agent moves at the moment of the change instead of ten minutes after it. Same outcome, a fraction of the runs, and nothing piled up behind itself.

The craziest jev demo I’ve seen so far

Let Superagent call for you, right from your WhatsApp or iMessage Powered by the new @OpenAI gpt-live-1, you feel the difference. (Want credits? Drop here a message)

You already know what your first Superagent task is. You just think it is too boring to count. People go hunting for something impressive instead. Impressive tasks are exactly the ones where you cannot say what a correct result looks like. Look for repetition. Go back through last week and find the thing you did more than twice that needed no judgment from you. The same lookup. The same copy and paste between two tools. The same file renamed and filed. Take the last one. A trigger fires when a file lands in your drive, the agent reads it, renames it to your convention and moves it to the right folder. You glance at the folder to see if it arrived where it should. That check takes seconds, which is the point. @Base44 Superagent already has every piece that needs. The trigger, the drive connector, its own file system, a browser when it has to look something up. The one piece it cannot supply is the convention, because a convention is a standard, and the standards are yours.

For your most complex personal assistant tasks Superagent by @Base44

Every now and then, I miss a meeting that is scheduled for the same day. My Superagent by @Base44 handles it now and makes sure I either decline or accept it, all via WhatsApp.

meeting ends. notes are already written. action items already listed. you didn’t do anything. your Superagent already knew you from email, slack and calendar. now it’s in your meetings too, connecting it all and building a place you and your Superagent actually get each other. @Base44

Introducing Superagent notes. Chat is a terrible place to keep anything. Not for the agent - for me, I'm the one who forgets. Superagent has Files, but I never remember where anything is saved or how it connects to everything else I’ve saved. So we built Notes. a new way you and your Superagent works together. Working with an agent no longer feels like a series of chats. You’re building something together—a shared memory you can both see, edit, and keep useful. It’s notes on steroids. A For You note surfaces what actually needs your attention: follow-ups, deadlines, decisions, and anything you’re blocked on. Meeting notes are there too, created by Superagent when it joins your meetings. And notes are linked to one another, turning scattered information into actual knowledge. The part I care about most is that it goes both ways. Superagent adapts to how you work and organize your stuff. Your context stops being something you have to hold in your head and becomes something you can actually look at. It's in Superagent, under Notes, Go put something in it. @Base44

This is insane. 850k agents built, actually changing lives and making a difference. Four months old. Give it another four.

Until now, onboarding to Superagent was: here's a chat. Good luck. We realized one of the hardest product problems isn't building an agent that can do things - it's explaining to you what it can do for you. So we rebuilt onboarding from scratch (honestly, we built one for the first time). And after a few hours of brainstorming with @OrlevYoav, we decided that instead of building just screens, we'd hand onboarding to the user's Superagent itself. Connect your email and calendar, and it gets to know you - then comes back with routines built around your week. Unanswered threads become draft replies. A pile of newsletters becomes one summary. No blank screen with a blinking cursor. No guessing. Your agent shows up already knowing you. And this is just the beginning, explaining what an agent can do for you is an infinite canvas, and cracking it will be some of the most important work we do.

Next level performance by the team, it’s a huge milestone and it’s just the start @Base44

Share your can’t is dead story and win this too cool for school hat 🧢 @Base44