Building RAG Systems That Don't Hallucinate
A practical guide to retrieval-augmented generation with hybrid search, cross-encoder reranking, and citation grounding.
Journal
The X1Y1 Journal
Deep dives into engineering, AI, and modern infrastructure. We document our learnings and architectural decisions. No fluff — just high-signal content.
Zero-Downtime Deploys on Cloudflare Workers
How we achieve atomic deployments with zero cold starts using Workers static assets and gradual rollout strategies.
MCP Servers in Production: Lessons Learned
What we learned deploying Model Context Protocol servers at scale — security posture, versioning, and observability gaps.
The Case for Edge-First Architecture
Why we default to the edge for new projects, and the specific scenarios where you still want a traditional origin server.
Fine-Tuning Open Models: A Cost Analysis
When does fine-tuning beat prompting? We break down the costs, latency tradeoffs, and quality deltas with real production numbers.
Stay Updated
Our journal is also published on Hashnode. Subscribe to get new articles in your inbox.
Subscribe via RSS