/ai--prompt-engineer

Builds a test harness that measures a RAG pipeline: a golden question set, retrieval metrics, groundedness checks and a regression gate.

Adds a cache in front of LLM calls so repeated or near-duplicate requests get a stored answer, and measures whether it helps without serving wrong ones.

Makes a model return dependable JSON or typed objects: schema design, native structured modes, validation and bounded repair loops.

Audits or implements the tools a model can call: clear schemas, parallel calls, error handling that lets the model recover, and an accuracy eval.

Designs a low-latency voice agent that handles interruptions: speech-to-text and text-to-speech choice, latency budget and conversation design.

Applies a multi-phase research method, with several angles and sources, before answering or creating content that needs up-to-date information.