About this Blog
There is more technical content than ever on platforms like YouTube and GitHub, but it's not always clear where to start or which workflows actually matter in practice. This blog is my way of sharing concrete, end-to-end examples from my work in cloud engineering, AWS, open-source tooling, and applied ML systems.
Posts focus on AWS and cloud fundamentals, infrastructure and deployment, observability, and open-source projects—reflecting my path as a cloud engineer and builder. My goal is for these posts to be directly useful: code you can run, ideas you can adapt, and workflows you can plug into your own projects.
Reach out if you're interested in contributing.
Evaluating Hybrid Guardrail Architectures for Prompt Injection Defense in LLMs
Systematic evaluation of baseline, regex-only, and hybrid guardrails on 625 prompts. Hybrid regex + LLM classifier achieves strong recall on standard and adversarial benchmarks—with full metrics and failure analysis.
Read article