Evaluation (evals)
Systematic tests that measure how well an AI system does its job.
For example
Running 500 real customer questions through a chatbot and scoring each answer.
Related terms
- API An application programming interface: a way for one program to talk to another.
- Deployment Putting software live, so real users can use it.
- Distribution shift When the real world looks different from the data the AI learned from.
- Git and GitHub Git tracks every change to your code; GitHub is a website where developers store and share it.
- Hackathon An event where teams build something that works in a short time.
- Open source Software whose code is public, so anyone can read, use and improve it.