Long-term knowledge is stored structurally, as embeddings, or as entities and relations, independently of single conversations. Typical conditions for use: The agent must utilise domain-specific knowledge long-term; Facts and preferences are reused. The central trade-off: Reusable, highly structured knowledge is gained against significant updating, modelling…
Use this profile to understand the building block briefly, place it in the model, and switch to the 360° assessment when needed.
Theoretical construct: explains a term, principle, or mental model.
What organizes, connects, or makes decisions possible.
Semantic memory stores information so a system can retrieve it through meaning, similarity, or relationships.
The approach combines ideas from knowledge representation, information retrieval, and neural language models. Vector databases made embedding-based similarity search practical; knowledge graphs add explicit nodes, edges, and provenance.
Imagine three card catalogs: one sorts by meaning, one by similar patterns, and one records links between cards. A good answer can find a relevant card and see its connections.
A numerical representation that captures semantic similarity.
Finding entries with similar representations.
Explicitly modeled entities, relationships, and sources.
Semantic memory can make large knowledge stores available to context-aware answers. It needs freshness, access controls, and quality checks; similar matches do not guarantee truth or completeness.
Where this building block is located in the topic model.
No structure path available.
Explore how this building block connects to concepts, methods, technologies, and tools.
These sources establish the term and its professional meaning.
All direct connections of the current building block in a compact text view.
This classification shows where the building block typically matters, how demanding it is, and what kind of impact it has in the model.
The level within the organization (enterprise, domain, team) at which the AssetBlock is applied.