Designing browser agents that fail safely
A practical workflow for browser automation agents with scoped tools, checkpoints, evidence, and recovery paths.
Read article ↗06 / BLOG
Notes for engineers who ship AI.
Practical field notes on computer vision, LLM systems, datasets, deployment, and building a career around useful technology.
How to design a production computer vision pipeline
A practical architecture for taking computer vision from a notebook to an observable, maintainable production system.
Read article ↗A practical method for optimizing computer vision inference
How to find the real bottleneck across decoding, preprocessing, GPU inference, tracking, and result delivery.
Read article ↗Building reliable LLM workflows beyond the demo
How to combine models, tools, retrieval, validation, and observability into LLM integrations that teams can trust.
Read article ↗Build an AI engineering portfolio that proves the work
A project structure that shows technical depth, product judgment, deployment experience, and clear communication.
Read article ↗Validate your vision dataset before training
The checks that catch expensive annotation and distribution problems before they become model problems.
Read article ↗Biology is becoming a software system
A practical way to think about the convergence of AI, biological measurement, intervention, and programmable medicine.
Read article ↗Five years of learning in public changed my career
How publishing simple technical tutorials created skills, opportunities, a global network, and a long-term personal brand.
Read article ↗Software engineering is the other 90 percent of production AI
Why useful AI systems require architecture, interfaces, deployment, scaling, and operations around the model.
Read article ↗Why computer vision remains a strong AI specialty
Real-time visual systems still require dedicated models, data, software architecture, hardware, and domain engineering.
Read article ↗Real-time dense 3D reconstruction with MASt3R-SLAM
What makes monocular dense reconstruction valuable, how the pipeline works, and what engineers should validate before deployment.
Read article ↗