AI engineering
in plain English.

Looking up relevant context from an external store (vector DB, docs, your own corpus) and stuffing it into the LLM prompt before answering. Reduces hallucination, costs less than fine-tuning, but adds a retrieval failure mode of its own.

A model architecture where each forward pass activates only a fraction of total parameters via a learned router. Mixtral, DeepSeek-V3, and Llama 4 use it. Bigger total parameter count, similar compute per token.

Open standard from Anthropic (Nov 2024) for connecting AI assistants to external tools, data sources, and prompts. Think "USB for LLM tools" — one protocol, many servers, any client.

LLM-driven loops that plan, take actions in the world (call tools, edit files, hit APIs), observe results, and iterate — rather than just answering a single prompt. The dominant 2026 paradigm for AI engineering.

Systematic measurement of LLM/agent quality — accuracy, hallucination rate, latency, cost. The discipline you wish you'd started 6 months earlier. Without it, you're shipping vibes.

A dense numeric vector that represents text (or images, audio…) in a learned semantic space. Cosine-similar vectors mean semantically similar content. The thing underneath every RAG pipeline.

The maximum number of tokens an LLM can consider per forward pass. 2026 frontier: 1M+ for some models (Claude 4.7, Gemini 2.5 Pro). Bigger window ≠ better answer — recall degrades inside long contexts.

The LLM emits a structured request to call an external function (search, calculator, API), the host runs it, the result goes back in the next turn. Foundation of every agent worth shipping.