Today, agents use software. Tomorrow, they use everything.
We're building toward a world where AI doesn't just click buttons on screens — it operates machines, navigates physical spaces, and works alongside humans in the real world.
Computer-use
Agents that see screens, click buttons, and operate any software exactly like a human would. No APIs needed. This is where Deck is today — and it's already changing how companies work.
Maximizing LLMs within today's limits
Current models are powerful but constrained — context windows, hallucination, cost. We're researching how to push further: multi-agent orchestration, long-running task memory, self-healing workflows that recover from errors without human intervention, and structured reasoning that keeps agents on track across 100+ step workflows.
Robotic-use
The same principles that let an agent navigate a website can let it navigate a warehouse. The same vision model that reads a dashboard can read a factory floor. We're exploring how Computer Use extends beyond screens — into cameras, sensors, robotic arms, and physical environments.
Open questions we're working on
APIs cover 1% of the world's software. The other 99% has only a user interface. How do you build an agent that can operate all of it — without a single line of integration code?
If the cognitive loop for navigating a website is the same as navigating a warehouse — perceive, decide, act — what infrastructure bridges the gap between digital and physical environments?
In a 200-step workflow where each step is 98% reliable, the end-to-end success rate drops to ~2%. How do you design error correction that keeps reliability above 95% without quadratic cost?
Every enterprise has thousands of credentials and every agent needs access. How do you build a credential architecture where no single VM compromise exposes the entire graph?
Software changes its UI faster than any model can retrain. How do you build agents that treat every interface as novel — and still operate it correctly on the first attempt?
What's the big question you're trying to answer?
If these questions excite you