Large language models — integration, prompt engineering, and production inference.
OpenAI and Anthropic both document outages, overload codes, and best-effort availability. The survival kit: LLM-aware circuit breakers, same-model-first fallback chains, and degraded modes designed before you need them.
One agent, one context window, one serial loop — until it stalls at 40 minutes and 180K tokens. The orchestrator pattern fans work out to isolated sub-agents in parallel, then synthesizes. Here's the backend, in compiling Go.
2,500 API endpoints in one MCP server without blowing context windows. The Code Mode pattern uses search + execute to cut token cost by 1,000x.
AI agents calling tools via MCP create new attack surfaces: prompt injection through tool responses, credential leakage, and unauthorized execution.
Compare pgvector, Pinecone, Weaviate, Qdrant, Milvus, and Chroma on performance, cost, and operational fit — with real code and each database's documented performance envelope.
Production LLM API patterns: streaming, function calling, retries, token budgets, cost optimization, and observability for backend engineers.
Build RAG systems that work in production: chunking strategies, embedding selection, pgvector ops, and retrieval quality evaluation.
Spring AI 1.1 deep-dive: production RAG pipeline with PII scrubbing, circuit breakers, Micrometer observability, and answer evaluation.