An AI job search platform used across 5+ countries — built on a deliberately unfashionable bet: humans before automation.
Tech professionals were losing 10–15 hours a week to applications: tailoring resumes by hand, re-entering the same fields on every platform, tracking it all in spreadsheets, with almost no signal on what was working. Kirro replaces that grind. Upload a resume once, and the platform matches, tailors, applies, and tracks every application for you.
My co-founder and I met at Meta and co-founded Kirro together. This case study covers the product side, which I lead end to end: strategy, research, UX, operations, and technical direction.
Research with 1,400 job seekers across the US, UK and Canada pointed to one answer: launch with humans, not automation.
"We relied on humans to learn what the automation should eventually do. We weren't being slow. We were being precise."
That hybrid model — a team applying on each user's behalf, guided by AI — paid for itself from day one while teaching us every edge case the automation needed to learn.
Kirro now runs across 5+ countries for tech professionals in product, engineering, design and data — applying to 200+ jobs a month per user, automatically.
The next phase of Kirro moves past automating applications. We're building a fully agentic job search assistant — AI that reasons and acts across a candidate's entire job search, from sourcing and tailoring to interview prep and offer negotiation, with a human always able to step in. That's what we're building right now.