Nerdy
AI
AI is only leverage if it lands inside a practice. These techniques cover where AI accelerates the work — discovery, delivery, decision-making — and where it just generates more for you to review.
AI Cost-Savings Scorecard
A 16-question self-assessment that estimates how much of your AI spend is structurally recoverable and ranks the levers that would recover it.
Compounding Engineering
Building reusable AI setups (projects, custom instructions, examples) that improve with use, turning one-time prompt wins into durable productivity systems.
Engineering Skills
Agent skills turn your team's engineering discipline into instructions a coding agent loads on demand. Four public libraries worth reading for reference, and why you should still write your own.
Evaluations
Systematic methods for measuring AI output quality so you can tell whether your prompts, context, and setups actually work.
Few-Shot Example Integration
How to wire a library of example files into Claude Projects, Cowork, and Claude Code so the right exemplars are selected per task and your quality bar compounds instead of resetting every session.
Meta-prompt Engineering
Using a model to build prompts as artifacts, either developing a reusable prompt on purpose or extracting one from a chat that already worked.
Prompt Frameworks
Six named structures for prompts — CO-STAR, RISEN, RACE, CREATE, APE, and STOKE — with the components each one forces you to specify and a decision matrix for picking one.
Reverse Prompt Engineering
Using AI to analyze successful outputs and reverse-engineer the prompts that would produce them, accelerating prompt development.