Practical articles on AI, DevOps, Cloud, Linux, and infrastructure engineering.
Use prompts to get reliable, safe outputs from LLMs for runbooks, code, and ops tasks.
We started routing 90% of LLM traffic through a small internal gateway. The gateway wasn't planned — it emerged from solving the same problem in 5 places. Here's the shape it took.
We benchmarked six embedding models on the same retrieval task. The results that surprised us, and how we'd pick today.
We cut our monthly LLM bill from $11,200 to $2,300 with seven specific changes. The ones that worked, the ones that didn't, and what we'd do first.
Fine-tuning is rarely the right answer. We've fine-tuned three times in two years; few-shot or RAG was correct for everything else. The decision criteria.
Multi-agent systems are mostly hype. The patterns we've seen actually deliver value, plus the ones we'd avoid until the tooling is more mature.
We tried four quantization techniques on Llama-3 and Mistral models. The quality vs cost trade-offs we found, plus what works for production inference.
We benchmarked four vector databases on the same workload. Each has a place. Here's how we'd pick today.
We've shipped four production RAG applications. Each one taught us something. The end-to-end pattern that works.
Run retrieval-augmented generation at scale. Chunking, caching, and observability.
A field report from rolling out retrieval-augmented generation in production, including cache bugs, bad embeddings, and how we fixed them.
Copilots suggest, agents act. Here's the spectrum between them, where each earns its keep in DevOps, and how to add autonomy without lighting your infra on fire.
