If senior engineers don’t start using AI tools today, they will be much slower than people who are using it.
Recently I talked with Doron, one of our founding engineers, who started using AI extensively during coding. He's able to finish whole features in a matter of hours. I chatted with him to learn about his secrets.I've been using AI to speed up my development process for over a year now—tools like Copilot and Cursor are great, but I just recently started noticing a huge impact. Doron surprised me with how quickly he was able to go from no code at all to a fully functional feature. He had a clear vision of how he wanted the feature to look, and with the right prompts, he got there without having to write much code himself.
Doron shared his experience with a feature called Composer within Cursor. It starts off like a chat, but it keeps the context of your work much better, remembering what files it touched and even creating new ones when necessary. This continuity means you don’t waste time reminding the AI what it's already done—it’s almost like working with another developer right beside you, someone who’s ready to answer your questions and do the tasks instantly.
Seeing Doron work, I realized something: there's a growing gap between those who use these AI tools effectively and those who don’t. If senior engineers don't start leveraging these tools today, they'll fall behind. Tools like Copilot, Cursor, and now Composer Mode can be the difference between staying competitive and falling behind.
What has your experience been like? What tools are you using?
We’re collaborating with our competitors and it can actually help our business (and our users!).
Last week I met Marc Klingen, the CEO and co-founder of Langfuse (YC W23). We recently started collaborating around OpenTelemetry and OpenLLMetry with the goal of standardizing the way customers monitor their LLM-based applications. The idea is simple - to start monitoring, you need to install an SDK. This requires a lot of engineering effort across your entire stack. If you’re using a standard like OpenTelemetry, you only need to do it once. You’re then never vendor-locked to a single platform.
Mark and I are both strong believers in open source and open protocols. Both of our products are open-source based, and we win by building the best product for our users - not by locking them in our own ecosystem. By using OpenTelemetry, we will benefit from consolidating the endless effort of supporting the new advancements in the LLM world. Every day there’s a new model that needs to be supported; a new vector database; or a new breaking change to LangChain. You’ll be surprised, but a significant part of our day-to-day work is actually keeping up with changes. For me, OpenAI DevDay was more of an endless list of backlog tasks that I now need to implement rather than an exciting event (just kidding; it was also super exciting - I’ll write about it more next week).
The future is open; in my opinion, open tools will always win. I always prefer them over closed tools whenever I can. And so should you.
*In the photo: enjoying a cup of coffee at Four Barrel SF
I think this is one of the most visually appealing features we've developed at Traceloop. I'm excited to announce that we now natively support all vision models (OpenAI and Anthropic included).
You can now see traces of vision-based flows with no limit on the payload size (well, except for the limit imposed by the LLM itself).
No matter whether you're sending images as base64, or URLs - we've got you covered! and all with <0.001ms impact on app latency thanks to our native OpenTelemetry support.
Huge shout out for Gal Kleinman my co-founder and CTO for building this 🙌
I've contributed to many open-source projects during my career and Hacktoberfest has always been the peak of it all. A whole month dedicated to advancing the great software that is building the Internet (and a chance to get lots of cool swag!).
So when Nevo David asked me to join DevFest AI with OpenLLMetry and Traceloop it was a no-brainer.
We're super excited to sponsor this special AI edition of Hacktoberfest!
Join us to contribute and advance the technologies that built the AI world. We have lots of talks, webinars, cool projects, and (of course) swag coming up this month. Register through the link in the comments below.
Don’t start a startup.
I’m not kidding. It’s the hardest job I have ever done.
But I want to focus on a small part of it - founder health. Or, more specifically - how and when to take some time off.
I just got back from a vacation, and I have to say it was really important, but it was almost impossible for me to disconnect.
As an early-stage startup CEO, and especially a technical one like me, I am in every bit and every detail. There’s always something happening that requires my attention. A customer needs help; a sales prospect is waiting for a follow-up; (I need to record my next Linkedin video); technical discussions, product discussions. Things are constantly buzzing.
Every decision I make actually and really matters.
But, I also want to enjoy my time off and founder health is really important.
Being able to recharge can do miracles for my own productivity and can keep me sane.
So what do I do? First, I delegate. My co-founder helps me take some of the load from me while I disconnect.
It’s also easier to do that once the company begins to grow. I didn’t take time off at all when it was just the 2 of us. But now we have 4 more people on the team, so I can allow myself to do that.
Second, and I know it may sound harsh, I try to keep it short.
I feel I can’t be gone for a month and expect everything to just work.
Lastly (and this still work in progress) I try to really disconnect. I turn off my slack notifications, and ask people to call me only if there’s something urgent.
As founders we are constantly focusing on customers, or revenue, or fundraising. But I believe we need to find some quiet time in between.
What are your tips for founder health?