01 / RESEARCHSmall Language Models
Less model. More focus. Exploring compact architectures built for well-defined tasks.
- Compact architectures
- Domain specialization
- Quantization
- Efficient deployment
Explore
Hard problems. New approaches. Useful intelligence.
These are the domains where we invest research and engineering effort. We explore them because they're hard, and because getting them right changes what's possible to build.
01 / RESEARCH
02 / RESEARCHModel Fine-Tuning & Training
Adapting general intelligence to specific contexts, data, and real-world constraints.
- Fine-tuning
- Domain adaptation
- Model training
- Dataset quality
03 / RESEARCHReinforcement Learning
How systems learn to act, explore, and improve through feedback rather than instructions alone.
- Reward design
- Planning & reasoning
- Policy optimization
- Experimental environments
04 / RESEARCHAI Agents & Multi-Agent Systems
Coordinated intelligence that uses tools, shares context, and operates within clear boundaries.
- Multi-agent architectures
- Tool use & orchestration
- Memory & retrieval
- Human approvals
05 / RESEARCHEfficient Inference & Evaluation
Knowing what works, what it costs, and where it fails — before a model reaches production.
- Inference optimization
- Evaluation design
- Reasoning reliability
- Performance & cost
06 / RESEARCHAI-Native Software Engineering
Rethinking specification, implementation, and verification with AI inside the engineering loop.
- Claude & Codex workflows
- AI-generated testing
- Architecture & review
- Custom AI applications
A note on honesty: these are areas of active exploration. We don't claim proprietary breakthroughs — we publish methods and findings in Lab Notes as they emerge.
From exploration to application
Research that ends in working systems.
Exploration isn't an end in itself. The same investigations feed our engineering work, our experiments, and the platform we're building.
Exploring a hard problem too?
If your challenge sits in one of these domains — or somewhere stranger — we'd like to hear about it.