Terms
- Retrieval Augmented Generation: Retrieval augmented generation, or RAG, is a technique that searches your own content at the moment a question is asked and puts…
- AI Agent: An AI agent is a system that works out which steps to take toward a goal and carries them out by calling…
- Fine-Tuning: Fine-tuning continues training an existing model on examples of the behaviour you want, adjusting its weights. It is how you teach a…
- AI Copilot: An AI copilot is an assistant built into software somebody is already using, which understands what they are working on and suggests…
- MLOps: MLOps is the practice of getting machine learning models into production and keeping them working there: deployment, monitoring, retraining and versioning. It…
Why these five
They are the terms that most often mean different things to different people in the same meeting. Getting them straight early saves a surprising amount of argument later, particularly the difference between retrieval and training, which decides how a system is built rather than how it is described.
Who writes these
The engineers who build the systems these terms describe. If a definition here disagrees with a vendor’s, it is because we have had to make the thing work in production. More about KoderTal.