About
I am an all-rounder with experience in Deep Learning, DevOps, and Full Stack Development. I built 2 products in the first startup I worked at (the second product launched successfully and now has 100+ customers). I continued my startup journey with a remote team. Currently, I'm working on my fourth product, Queryloop.ai. I hope to one day create my own product. I've recently started on the side and give it some time on the weekends. I hope to share that one day as a side project. For now, the focus is helping my current team grow beyond its first user. You're welcome to connect with me on LinkedIn. I share my learnings all the time.
Work
Engineering at Queryloop
Links
Badges
Maker History
- QueryloopBuild production-ready RAG applications 100x faster
Forums
Do you remember how you made your first internet dollar?
In a time when everyone is sharing their 6-figure MRRs from their businesses, it s sometimes worth taking a look back at how we started (and maybe even finding joy in the little things). :-)
Do you still remember the moment you received your first online payment?
The questions I get most often about Product Hunt and answers
During the week, I receive a lot of questions about Product Hunt, and some of them are very frequent. I thought I would post the most frequent ones here, and a possible answer to them.
Is it worth having a hunter?
If the hunter has a large follower base, a strong community, and a good reputation (and your product is also good, i.e. it will be featured): YES, IT IS WORTH HAVING A HUNTER. It will multiply your visibility and success
Challenges that I'm currently working on in the development of AI Agents
So here are 3 problems that I'm working to solve in the development of our agentic systems.
Any help would be truly appreciated.
1) How to prevent the agent from leaving the loop in between tool calls, saying it's "going to move on to the next step", or to ask the user for confirmation.
2) How to make the agent manage it's tokens autonomously and intelligently, by identifying and discarding messages or context that are no longer relevant.
(Important in particular for when there's this one gigantic piece of content among the messages that keeps getting sent back in each new API call, making the token count grow exponentially)
- One path that I'm exploring is to have the one task or step in a different agent, so the main agent calls the agent that executes this task, so the context stays separate.