Context and knowledge

Agent memory

A system for capturing, retaining, selecting, and delivering prior state so it can influence an agent's later decisions.

Chunking

Splitting documents or data into retrieval units that can be indexed, selected, and placed into model context.

Context rot

The degradation in an agent's ability to find, follow, or correctly weigh relevant information as its accumulated context becomes longer, noisier, stale, repetitive, or internally conflicting.

Durable memory

Agent state intentionally retained across runs and made available later, with explicit ownership, provenance, retention, and correction rules.

GraphRAG

A family of retrieval-augmented generation methods that builds or uses graph structure to retrieve relationships, communities, paths, or corpus-level themes.

Knowledge graph

A graph-shaped representation of entities or concepts and their named relationships, often governed by a schema and linked to supporting sources.

Prompt caching

Reusing model computation for an unchanged prompt prefix or context block across requests to reduce repeated input processing, latency, and cost.

Prompt compression

Reducing the tokens sent to a model while attempting to preserve the instructions, evidence, state, and relationships needed for the task.

Reranking

Rescoring an initial candidate set with a second model or rule to improve its ordering before selection.

Retrieval-augmented generation (RAG)

Generating a response after retrieving relevant material from an external knowledge source and adding it to model context.

Semantic search

Retrieval that compares learned representations of a query and candidate items instead of relying only on exact term overlap.

Vector database

A data system that stores vectors with identifiers and metadata and supports similarity search over them.

Working memory

The bounded task state actively delivered to an agent during a run, including current goals, constraints, observations, and pending work.