Sanchal Ranjan

making the numbers work - lately, with a fleet of AI agents

I've spent 14+ years building three companies. ZiffyHomes (YC S18) hit $10M ARR in two years and exited to a Tiger Global portfolio company. Analog raised $21M+; its layer-1 mainnet reached a $300M+ cap. Now I'm building Pocodot as co-founder.

These days I ship through AI agents the way I used to ship through engineering teams. The job didn't change, but the team did.

writing

• The Model-Routing RubricModel choice is a P&L decision. The rubric I use to route every task to the cheapest model that clears the bar.
• Agents Are the Primary CustomerThe best new infra companies sell to software, not people. Chosen once by an agent, used indefinitely.
• The P&L LensStart from the number that has to move, then decide what AI is worth building. Not the other way around.

now

July 2026 - building an agent stack that keeps working when I stop, and writing down what it teaches me. More here.