Harsha

Its amazing what an individual going crazy with all the AI noise on LinkedIn can do when he/she decides its time to get the 'hands dirty' :) but still has the Impostor syndrome after seeing what the community on PH is doing ! Thats me :)
Currently, I am the architect of AdvisorSprint, a proprietary 12-agent AI system designed for institutional-grade strategic analysis across CPG and B2B sectors. My work focuses on moving beyond "wrappers" to true AI orchestration that scales competitive intelligence. Each agent's foundation is built on my 21 years of consumer understanding and how categories are created, nurtured & scaled.
I am not a techie ( Prior to now, I had coded in php 22 years ago! ) and hence this orchestration has been all the more exhilarating. This tool is a text-book definition of a scrappy project, but one that produces institution-grade analysis, appreciated and acknowledged by the best in the industry ! I would love to share and get feedback on the architecture and improvements that can be made.

A couple weeks ago, Boris Cherny (the creator of Claude Code) shared a bunch of really useful tips on getting the most out of Claude Code. #1 at the top of the list: do more in parallel. He himself runs 10-15 Claude codes in parallel.

His advice and practice makes sense: coding agents give us the ability scale infinitely. At this point, the only real limiter is our own ability to manage all of these agents.