A

ai-evaluation

Case study of a pre-alpha Algebra I tutoring platform focused on hybrid AI/deterministic architecture, multi-provider LLM evaluation, safety controls, and measured cost/latency tradeoffs.

Production-grade toolkit for evaluating RAG (Retrieval-Augmented Generation) pipelines.

Proof-Adjusted Autonomy (PAA): the metric of independently proven AI agent work — a 90% autonomous agent is a 61.6% agent. Coined by Michał Piszczek. Mirror of github.com/pich/proof-adjusted-autonomy.

Next.js + Prisma full-stack interview prep with deterministic AI scoring pipeline, OpenAI-backed evaluation worker, and seeded question templates.