Hi, I’m Samuel. I’m documenting my DevRel journey as I live it.
This space is where I share thoughts, experiments, wins, and hard lessons from doing developer relations in real time. No heavy tooling. Just honest reflection and practical notes from the field.
Latest Writing
See all posts-
How Plan Caching Reduces LLM Agent Costs
Plan caching reuses planning templates across similar agent tasks, cutting cost and latency without throwing away accuracy.
-
Stop filling your agent's context window just because you can
Bigger context windows do not remove failure modes. They create new ones when we stop being intentional about what goes into an agent's context.
-
I benchmarked 5 embedding models across 4 datasets
I benchmarked five embedding models across four NanoBEIR datasets and found that bigger embeddings did not always produce better retrieval.