Insights on autonomous AI for health and robotics — from predictive health twins to world models for robots.
Before USB-C, every device had its own cable. Before MCP, every AI integration was a snowflake. Why we're standardizing on Model Context Protocol as we build the Baxter Labs stack — and the three patterns we're leaning on most.
Skills, tools, and agents are not the same thing — and picking the wrong one is the fastest way to overcomplicate the AI product you're building. The decision tree we're using as we build at Baxter Labs, plus three failure modes we keep watching out for.
Notes from inside the build — Aeiva is the longevity app and AI health twin we're building at Baxter Labs. Here's what we're seeing so far: data is dirtier than expected, uncertainty needs to be surfaced not hidden, and the model is rarely the actual product. Sharing as we go.
The founder's manifesto for Baxter Labs. Why Reality. Synchronized. is a thesis about the next decade of AI, the gap we're trying to close, and the two products operationalizing it — Aeiva (consumer health twin) and AEDT (agentic OS for robotics).
Get new writing on AI for health and robotics delivered to your inbox.
We use a small amount of analytics data to improve Baxter-Labs. No data is sold, ever. You can change your mind anytime in our Privacy Policy.
