lauren flipo

Congrats on shipping this, the vision-based approach vs DOM scraping is the right bet. One question: once your agents are running scheduled tasks autonomously, how do you get visibility into what they're actually doing at the prompt/response level? We ran into this with local agent stacks and it became a serious blind spot. That's what Veil-Piercer solves, curious if browser agents hit the same...

Hey PH! 👋 Lauren here, maker of VeilPiercer. Quick backstory: I built this because I was running 6 AI agents locally and had zero visibility into what they were doing. Every cloud monitoring tool added costs on top of already-expensive model calls. I wanted something that ran on my own hardware and cost a flat rate forever. So I built an AI swarm that monitors itself. The agents score each...

Hey PH! Lauren here, maker of VeilPiercer. I built this because I was running 6 AI agents locally and had zero visibility into what they were doing. Every cloud monitoring tool added costs on top of already-expensive model calls. So I built a swarm where agents score each other every 35 seconds using a REWARD model. The highest-scoring agent gets flagged as MVP. Lessons get written back to...

one of these days , one of these days .....!!!!