About this blog
This blog is a place to document software engineering and applied AI through real problems, experiments, and implementation work.
The topics usually grow out of something I am building, studying, debugging, or trying to understand more deeply, from Python backend development and asynchronous programming to RAG pipelines and LLM applications.
Rather than presenting technologies as a collection of ready-made recipes, I try to document the reasoning behind technical decisions: what I expected to happen, what actually happened, what failed, and what I learned from it.
Here, you will find:
- Python, FastAPI, APIs, async programming, testing, and backend architecture
- Applied AI topics such as LLM applications, RAG, embeddings, retrieval, and evaluation
- Technical experiments and design decisions from hands-on projects
- Debugging notes, configuration issues, development tooling, and lessons learned while building systems
- Practical analyses of behaviors that are easy to overlook when following documentation or tutorials
Some posts will be deep technical investigations. Others may be shorter engineering notes about a configuration problem, an unexpected behavior, or a solution that may be useful again later.
The common thread is not a specific framework or technology. It is the process of understanding how things work well enough to make better engineering decisions.
Readers do not need to follow the code to understand the conclusions, but they can, if they choose to go deeper.
Why this blog exists
Good engineering decisions usually come from understanding behavior, not just memorizing APIs.
I use this blog to slow down and examine the details that are easy to skip while building software: why a certain implementation behaves differently than expected, what trade-offs exist between alternatives, how a configuration affects a system, or what an experiment reveals about a design decision.
Writing these notes also turns problems solved once into knowledge that can be reused in future projects.
The goal is simple: build, investigate, understand, and document what is worth remembering.
If you are interested in Python, backend engineering, applied AI, and the reasoning behind technical decisions, this space is for you.