01
RL environments & infrastructure
Company-scale simulations with real codebases and microservices, allowing agents to master the complex, long-horizon workflows required for production.
Data Research Lab SF Bay Area
Build environments that enable agents in the real world.
Bespoke Labs
Reliable agents need [ real ] environments.
Trusted by Research Teams
0+
teams using GEPA in production
0k+
monthly downloads of OpenThoughts on Hugging Face
Cited
in Claude 4.5 release notes (Terminal-Bench)
Environment research & infrastructure for the agent revolution.
[ Frontier Labs ]
[ Neolabs ]
[ Enterprises ]
/ 01
What We Do
As AI agents move from demos to production, the bottleneck for reliability is no longer the model, it’s the environment.
We are an applied AI research lab building the environment infrastructure for the agent revolution.
02
Agent evaluation & optimization
Automated prompt and policy searches via the GEPA optimizer achieve superior accuracy significantly faster than traditional, manual prompt engineering.
03
Production-grade RL & benchmarking
Collaborative research in RL, curation, and benchmarking ensures that training environments keep pace with the rapidly advancing frontier of model capabilities.
/ 02
Who We Serve
Two audiences. One foundation: real environments.
[ For Frontier & Neo Labs ]
Train in environments that match production.
Use our environments as training grounds to teach new tasks and improve reliability.
[ For Enterprises ]
Build AI that doesn’t break in production.
Enterprises rely on us to make AI agents dependable. With Bespoke, you can:
- Evaluate agents in environments that mirror your systems and processes.
- Optimize prompts and policies automatically with GEPA and RL.
/ 03
Our Research Track Record
We ship products. And we advance the field.
This combination of open research, benchmarks, and deployed optimization infrastructure makes Bespoke the environment partner of choice for the agentic era.
01
OpenThoughts
One of the best open reasoning datasets.
02
Terminal-Bench
First environment-based benchmark for agentic systems.
03
GEPA
Evolutionary algorithms for prompt optimization.
/ 04
Get in Touch
Join us in building the foundation for the agentic world.
Join the Team
Full-time researchers and engineers who want to do the most important work in AI, not just the most visible.
See open roles →Build with us
Domain experts interested in building RL environments and data pipelines.
Apply as expert →Work with us
Frontier labs or enterprises looking to improve agent reliability.
Start a conversation →