Glossary
The AI support glossary
The concepts behind a knowledge-trained support assistant, explained for support and ops teams. Each term is one CertifChat actually relies on under the hood.
Browse terms
- ChunkingSplitting documents into passages small enough to embed and retrieve precisely.
- EmbeddingsNumeric vectors that capture the meaning of text so similar passages sit close together.
- HallucinationWhen a language model states something confidently that isn't supported by its sources.
- Knowledge BaseThe collection of content an assistant draws on to answer questions.
- Retrieval-Augmented Generation (RAG)Grounding an LLM's answers in retrieved source documents instead of its training data alone.
- Semantic SearchSearching by meaning using embeddings, often combined with keyword search.
- Ticket DeflectionResolving customer questions automatically so they never become support tickets.
- Vector DatabaseA store optimised for finding the embeddings most similar to a query vector.
Put your knowledge to work today
Connect your sources, drop one snippet on your site, and start deflecting tickets. We are opening CertifChat to a first group soon.