note: this site's design and placeholder content were generated with AI assistance
vitalii@web: ~/blog
📂 blog on main using 🐍 3.14.2
$ uv run python3 print_me.py
📂 blog on main using 🐍 3.14.2
$ uv run python3 -i blog.py
>>> Blog.objects.order_by("-date")
"Building Reliable AI Pipelines in Production"
# What I learned running LLM-powered pipelines for 18 months.
"Structured Output from LLMs: Beyond JSON Mode"
# Getting models to return data you can actually use in typed Python code.
"Why I Still Write Raw SQL in 2025"
# A defense of keeping SQL close to the metal at scale.
"Observability for Python Services That Actually Helps"
# Logging, tracing, metrics — getting the basics right.
"FastAPI Patterns I Keep Coming Back To"
# Dependency injection, background tasks, and middleware that survive production.
tmux
0:home* 1:twitter 2:github
blog