PRACTICE
RAG
Retrieval that supplies selected source material to a model before generation.
DEFINITION
RAG definition
Retrieval augmented generation, or RAG, gives a language model selected source material at request time before it writes an answer. The retrieval layer determines what can be found, while citations and evaluation show whether the answer remains grounded in that material.
WHY IT MATTERS NOW
The current operating pressure
Teams are moving from general model demonstrations to systems that must answer from private, changing material. Retrieval quality, document permissions and measurable answer quality now determine whether those systems are useful.
WHAT WE DO ABOUT IT
Work connected to RAG
AI assistants and agents
Retrieval over your own documents, tool access scoped by role, a human in the loop on anything customer facing.
Retrieval over your documents
A working retrieval layer over your own material, with the ingestion, chunking and permission rules written down.
NEIGHBOURING TAGS
Shared parts of the map
Edge width follows the number of shared nodes
RAG at the centre, 1 neighbouring tags around it: AI agents (2 shared nodes).
- AI agents
2 shared nodes
Trace the shared concern through your systems
Bring the system boundary and the decisions that need evidence. We will identify the connected work and define a practical starting point.