See inside the lab
A Skillful Gorilla Division

The Other Domain

Experimental AI research. The place where we build things that might work, might not, but will definitely be interesting.

Conversational Intelligence

Agents That Understand

Building AI that holds context across complex, multi-turn conversations. Not just responding — actually following along.

Active experiments

Conversational Agents

In Progress

Building AI agents that can hold context across complex, multi-turn conversations. Testing the boundaries of coherence.

Semantic Memory

In Progress

Experiments in long-term memory for AI systems. How do you remember what matters and forget what doesn't?

Tool Orchestration

Research

Giving AI systems access to external tools and seeing what happens. Spoiler: it gets complicated fast.

Reasoning Chains

Planning

Breaking down complex problems into steps. Making the thinking visible and verifiable.

Multimodal Inputs

On Hold

Processing images, audio, and text together. Waiting for the right use case to emerge.

Autonomous Workflows

Research

AI that can plan and execute multi-step tasks without hand-holding. What could go wrong?

How we work

  • 01Start with a question, not a product. The interesting stuff happens when you're exploring.
  • 02Build fast, document everything. Failed experiments are still data.
  • 03Share what we learn. The field moves faster when people aren't duplicating effort.
  • 04Stay curious. The moment you think you understand AI is the moment you've fallen behind.

Got an idea?

We're always looking for interesting problems to work on. If you've got something that doesn't quite fit anywhere else, it might fit here.

Submit an idea