RunRL
RunRL is a YC Spring 2025 (P25) company. Based in San Francisco, CA, USA. Team of 3.
About RunRL
Summary
RunRL delivers reinforcement learning as a service, helping AI teams improve the performance of their LLMs and agents on specific tasks. Customers supply a model, a prompt, and a reward function; RunRL handles the training to push that reward higher. The service replaces manual prompt engineering and the guesswork of repurposing observability data for model improvement, and has been applied to domains including interpretability, formal verification, drug design, and automated red-teaming.
Business model
Fee-based service engagement, initiated by email or a booked call.
Go-to-market
AI teams at B2B companies seeking task-specific model improvement are the target buyers; they enter through direct outreach via email or a scheduled call, indicating a sales-assisted motion.
From the Y Combinator listing
Reinforcement learning as a service
RunRL improves LLMs and AI agents with reinforcement learning. Do you have a model that needs to get better at a certain task? Are you tired of messing around with prompts? Do you spend a lot of money on observability, and wish that all this data could let your model self-improve? Well, head on over to RunRL.com, and see what we have to offer! If you give us a model, a prompt, and a reward, we’ll make your model’s reward go up.
Facts
- B2B / B2B -> Infrastructure
- San Francisco, CA, USA
- 3
- Active
- Early
Founders (2)
- Derik Kauffman
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