Context Window
The bounded span of tokens a model can attend to in a single inference, containing the prompt, retrieved material, and conversation so far.
Why it matters
The context window is a hard architectural limit, not a memory system. Confusing the two produces designs that silently drop the evidence a decision was based on.
What it is not
These are routinely confused with Context Window. The distinctions are not pedantic — each one has consequences for how a system is governed.
The window is per-inference and ephemeral. Memory persists across invocations and is a separate, governable artifact.
The window is runtime input. Training data is baked into weights and cannot be inspected per-decision.
Relationships
Typed edges into the rest of the ontology. These are what make the canon traversable rather than merely readable.
| Verb | Target | Meaning |
|---|---|---|
notEquivalentTo | Agent Memory | The two are routinely conflated and are distinct. |
Record
| Canonical identifier | QIS-TERM-00009 |
| Status | Canonical industry term |
| Adoption | Widely used |
| Domain · Layer | Context & memory · Intelligence |
| Origin | Language model architecture; universal usage. |
| Semantic aliases | None recorded. |
| First published | 2026-08-02 |
| Last reviewed | 2026-08-02 · 180-day cycle |
Cite the identifier, not the URL. Identifiers are stable; URLs may change. This entry is free to read, quote and index under the dual license. Corrections to [email protected] are published.