Papaya
Papaya is a YC Fall 2026 (F26) company. Based in San Francisco, CA, USA. Team of 3.
About Papaya
Summary
Papaya builds an optimization engine for AI agents already running in production. It connects to an engineering team's agents via SDK, scans production traces across prompts, context, tool calls, subagents, and models, and surfaces ranked recommendations to fix problems like context bloat, excessive tool calls, and serial API calls. Each approved fix is pushed directly to production as a pull request, replacing the manual work of reading traces and diagnosing agent inefficiencies by hand.
Business model
Priced per workflow at an annualized rate, targeting large-scale deployments.
Go-to-market
Engineering teams at companies running AI agents in production are the buyers; they start through a self-serve SDK install that delivers a first ranked finding in under 15 minutes, with demo requests available for larger accounts.
From the Y Combinator listing
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.
Facts
- B2B / B2B
- San Francisco, CA, USA
- 3
- Active
- Early
Founders (3)
- Macy Mody
- Niyaz Puzhikkunnath
Score every batch against your own thesis
GPAgent's sourcing agent reads every company in a batch, scores each one against your fund's thesis in a private workspace, and lines up the founders worth meeting before Demo Day. You decide who to contact. Your scores, notes, and pipeline never appear on these pages.
How Accelerator intelligence works