Language Model
Also called LLM
A language model learns patterns in language and uses supplied context to produce a response. In an agent application, it can propose the next action; surrounding software carries out that action.
[Anthropic]In practice · hypothetical example
A writing assistant receives a paragraph and proposes a clearer version.
[Anthropic]A little deeper
A model response can include a request to use a tool. The surrounding application provides the tool result for a subsequent response. [Anthropic]
What produces the proposed response?
Sources & editorial notes
Evidence: supported. Primary-source support for this scoped entry; publication approved by the project owner.
- Building effective agents ↗ (opens in new tab)Anthropic · 2024-12-19
Relevant section: What are agents?; Building blocks; Agents; Appendix 2
Last editorial review: 2026-09-13 by project-owner.
First observed in this corpus: Unknown.
Revision history
Revision 2 · Created 2026-09-12 · Updated 2026-09-13
Project owner approved the current content for publication. Existing evidence scope and limitations remain applicable.