Continuous optimization for AI agents
Papaya is the optimization engine for AI agents. Engineers don't have time to continually improve the agents they've shipped — the context bloat, overly chatty subagents, and broken tool calls sit in production traces nobody reads, quietly hurting agent efficiency. With Papaya they connect their agent directly via SDK, get actionable recommendations on how to improve quality, latency, and cost, and the ones they approve are pushed to production as pull requests. Papaya runs 200+ research-backed analyses across context, prompts, prompt caching, subagents, and tool calls. Every recommendation is ranked by impact and comes with the production runs that produced it — typically a 10%+ quality improvement on the first workflow analysis.
Founder/CEO
Co-Founder & CEO at Papaya (YC F26). Previously led GTM and Ops at SafeBase from $0-10M ARR and through its acquisition. Also built analytics products at HqO and managed investments for Amex Digital Labs. UMich undergrad and HBS MBA.
Founder/CPO
Founder at Papaya. Previously Sr. SDE at Amazon for several years building large-scale ML systems across Computer Vision, Classification, LLMs/Agents. Led work on brand and product classification, built agent evaluation workflows, and created a self-service ML training pipeline. Earlier, an early engineer at Zovi.com, where he helped build the front-end architecture and internal analytics.
Founder
Founder at Papaya (YC F26). Previously Senior Data Engineer at Amazon for 10 years, leading teams for the enterprise Data Lake, solving problems at Exabyte scale. Earlier scaled Vodafone's MPESA mobile money system in Africa from 25 to 200 tps at IBM. Co-founded OpenReporting, a SaaS financial reporting tool.
