# gogoai.dev

> A curated discovery feed for SRE, AIOps, Platform, DevOps, and Cloud Ops engineers. News, products, jobs, events, CFPs, and community content in one fast feed.

## Sections
- [Feed](https://gogoai.dev/): Curated news, products, and community content for ops engineers.
- [News & Blogs](https://gogoai.dev/news): The latest news and engineering blog posts, newest first.
- [Blog](https://gogoai.dev/blogs): Original writing on SRE, AIOps, Platform, DevOps, and Cloud Ops.
- [Jobs](https://gogoai.dev/jobs): SRE, DevOps, Platform, and Cloud Ops job listings with filters.
- [Product Launches](https://gogoai.dev/products): New tools and products for ops engineers.
- [Events](https://gogoai.dev/events): Conferences and meetups for the ops community.
- [CFPs](https://gogoai.dev/cfps): Open calls for papers.
- [Memes](https://gogoai.dev/memes): Ops humor.

## Blog posts
- [The Quiet Defeat of Vector Databases: How Knowledge Graphs Became the Backbone of Enterprise AI](https://gogoai.dev/blogs/quiet-defeat-of-vector-databases): Why teams running real enterprise AI workloads are quietly migrating from vector databases to knowledge graphs — and what it means for cost, latency, and model size.
- [The Future Economics of Enterprise AI Deployment](https://gogoai.dev/blogs/future-economics-of-enterprise-ai-deployment): Frontier API access is a structurally expensive, strategically fragile bet at scale. The winning architecture minimizes tokens consumed per unit of business value.
- [How to serve LLMs in production: a guide to GPU memory, KV cache, and sizing](https://gogoai.dev/blogs/how-to-serve-llms-in-production): Weights, KV cache, and engine overhead all share VRAM. A practical guide to sizing a GPU for multi-user LLM serving — with the formula and worked examples.
- [Anatomy of an LLM request: prefill, decode, latency, and cost](https://gogoai.dev/blogs/anatomy-of-an-llm-request): Every LLM request splits into prefill (compute-bound, sets TTFT) and decode (memory-bound, sets TPOT). Understanding both is how you control latency and cost.
- [Building LLM applications: RAG, agents, tool calling, and reasoning](https://gogoai.dev/blogs/building-llm-applications): RAG, tool calling, and agents are the three building blocks. Default to the simplest architecture that works — a 5-step agent costs 5x and fails 5x more.
- [LLM serving cheat sheet: GPUs, models, vLLM flags, and cost levers](https://gogoai.dev/blogs/llm-serving-cheat-sheet): A single-page reference for serving LLMs in production: vocabulary, sizing formulas, GPU and model tables, essential vLLM flags, and cost levers ranked by impact.
- [Common mistakes when serving LLMs in production: a field guide](https://gogoai.dev/blogs/llm-serving-common-mistakes): 24 real production LLM mistakes — from deploying Ollama for multi-user to unbounded conversation history — each with the fix. Read it before you ship.

## Optional
- [Full text](https://gogoai.dev/llms-full.txt): Expanded index with post summaries inline.
- [Sitemap](https://gogoai.dev/sitemap.xml)