An AI SDK doesn't make the model smarter — it deletes the streaming parser, the tool-calling loop, the JSON-validation prayer, and the per-provider glue you'd otherwise hand-roll against a raw HTTP endpoint. Here's exactly what you get over `fetch`, using the Vercel AI SDK, and where the abstraction leaks.
Skip the protocol theory. Build a working Model Context Protocol server in TypeScript, wire it into Claude Code, and make a real agent call a real tool in under an hour. Code, traps, and how to know it works.
Prompt engineering was about wording one message. Context engineering is about managing the entire context window as a scarce budget — what goes in, in what order, and what gets evicted. For a backend engineer, it's working-set management applied to an LLM.
A normal cache keyed on the exact request string is almost useless for LLM calls, because every paraphrase is a miss. Semantic caching keys on meaning instead — embed the query, search for a near-identical past question, and return its answer with no model call. Here's the architecture, the threshold problem that makes or breaks it, and real pgvector code.
How to migrate a production Angular app from 17 to 21 — control flow, standalone components, signals, inject(), and zoneless change detection.