Golden dataset
A carefully chosen set of example inputs with agreed good answers, used to run evals. It should include ordinary cases, edge cases and past failures. It needs maintaining as the real work changes.
Related terms
A way for software to talk to other software. AI providers offer APIs so developers can send prompts and receive outpu…
API keyA secret string that identifies your account when your code calls an API, and that the bill is charged to. Treat it li…
AgentAn AI system that works towards a goal over several steps, deciding which tools to use and acting on the results with …
Agentic workflowA process where an AI model decides some of the steps itself, rather than following a fixed sequence. It handles messy…
Batch processingSending many requests together to be processed in the background over a longer window, rather than waiting for each in…
BenchmarkA standard public test used to compare models, such as sets of exam questions, coding problems or maths puzzles. Usefu…
Knowing the word is the easy part
A short assessment scores you across five skill areas and builds a path through 18 modules, skipping whatever you already know. Free, no card.
Find your level