Robotics, embedded Linux, and applied AI systems.

Personal engineering workbench of Shawn Maybush. Focusing on closed-form kinematics, hardware abstraction layers, containerized toolchains, and distributed autonomous agents.

Recent Lab Notes

2026-11-06
The Death of Prompt Whispering: Why Systems Architecture Beats Clever Prompts#ai#systems-engineering#context-engineering
Why natural language begging rots in production, and how bounded workspaces, deterministic file primitives, and actionable error contracts make autonomous agents reliable.
2025-01-06
Solving Inverse Kinematics with Dual Quaternions and Polynomial Regression#robotics#inverse-kinematics#dual-quaternions
Using dual quaternions and JAX-accelerated polynomial regression to solve inverse kinematics for robotic manipulators with low-overhead edge inference.
2024-09-09
Prompt Engineering for Structured Output with Google AI Studio and Vertex AI#ai#prompt-engineering#gemini
Refactoring LLM prompts for OpenAPI response schemas, JSON mode, and robust system instructions using Google AI Studio and Vertex AI.
2024-08-23
Building a Dockerized I²C Development Platform for Raspberry Pi#robotics#raspberry-pi#docker
Creating an isolated ROS2 development and testing platform with C++ I2C drivers, i2c-stub emulation, and Docker container passthrough on Raspberry Pi.
2024-08-17
GitLab Code Reviews with Gemini Pro 1.5#ai#gemini#gitlab
Automating code reviews and documentation updates within a GitLab CI/CD workflow using Google Cloud Functions and Vertex AI.

View all lab notes →