Blog

Thoughts & Stories

Sharing my experiences, learnings, and adventures in tech and beyond.

Browse by Topic

DevOps & Cloud Infrastructure (138)AI & LLMs (102)Web Development (81)ERP Systems (72)Backend & APIs (60)Software Development (52)Security (28)Career Reflections (27)Cloud (15)Product & SaaS (12)AI / Machine Learning (5)University (1)Hackathons (1)

Stock Opname in ERP: Cycle Counts Without Freezing Ops

ERP

July 20269 min read

Stock Opname in ERP: Cycle Counts Without Freezing Ops

How to design stock opname in a custom ERP so it stops being a once-a-year freeze: snapshot vs live counting, ABC cycle-count scheduling, variance approval, and correct adjustment posting.

GitHub Actions OIDC: Keyless Cloud Auth for CI/CD

DevOps

July 20269 min read

GitHub Actions OIDC: Keyless Cloud Auth for CI/CD

Long-lived AWS and GCP keys sitting in repository secrets are a standing liability. Here is how to replace them with GitHub Actions OIDC federation, trust policies, and subject claim scoping.

July 20269 min read

LLM Structured Output: JSON Schema That Actually Validates

Prompting an LLM to return JSON is not the same as guaranteeing it. Here is how JSON Schema constraints, tool-based calling, and Zod validation turn probabilistic output into something you can trust in production.

July 202610 min read

LLM Evals in CI: Testing Prompts Like Code

A prompt change that looks harmless in a chat playground can quietly break a production feature. Here is how to build an evaluation harness that catches that regression before it merges.

Choosing an Embedding Model: A Practical Benchmark

AI/ML

July 20269 min read

Choosing an Embedding Model: A Practical Benchmark

A practical framework for picking an embedding model for RAG: dimension versus cost versus recall, why MTEB scores can mislead you, and a script to benchmark candidates on your own data.

Hybrid Search and Reranking: Better RAG Retrieval

AI/ML

July 202610 min read

Hybrid Search and Reranking: Better RAG Retrieval

Boost RAG accuracy with hybrid search and reranking, fusing BM25 keyword search with vector search, then reranking with cross-encoders before generation.

Showing 307–312 of 594 posts

Explore More

Projects

See the projects I've built

Experience

My professional career

Certifications

Professional certifications