Articles

Notes from production

Field notes on shipping AI you can trust — evals, RAG, agents, and the engineering discipline around them.

HTTP caching with Cloudflare's CDN

How cache headers in _headers plus Cloudflare's edge make a static site feel instant on repeat visits and almost free to serve — the full per-file policy.

CachingCDNPerformance

Email DNS: MX, SPF, DKIM, DMARC

How domain email works: MX delivers your inbound mail (checked by the sender), SPF/DKIM/DMARC prove the outbound (checked by the recipient), and using it in Gmail.

EmailDNSDeliverability

Why “faithfulness ≥ 0.90” should gate your deploys

A practical look at turning eval scores into a CI gate — and what to do when a release fails it.

EvalCI/CDRAG

Hybrid retrieval + reranking, explained

BM25 vs dense vs hybrid, and why a reranker is usually the cheapest accuracy you can buy.

RAGRetrievalReranking

Red-teaming an LLM app before users do

Jailbreaks, prompt injection and PII leakage — a checklist mapped to the OWASP LLM Top 10.

SecurityRed-teamOWASP

Agentic RAG without the runaway costs

Tool-use orchestration with guardrails on every hop, and how to keep the bill predictable.

AgentsCost controlRAG

Self-correcting answers with CRAG & Self-RAG

When to retry retrieval, when to abstain, and how to wire the feedback loop.

RAGCRAGSelf-RAG

Observability for LLM systems that actually helps

The traces, metrics and cost signals worth wiring from day one — not after the incident.

PlatformObservabilityOps