Glossary / Core concepts
Language as runtime execution layer
In modern AI systems, prompts, instructions, retrieved context, memory, summaries, rubrics, policies, and tool schemas can function as part of the system's execution path, not merely as descriptions around it. Hermes Labs refers to this as the language runtime execution layer: the operational layer where meaning, constraints, evidence, and behavior are shaped before and during model use.
How it manifests · Tool-addressed
It shows up whenever a change to a prompt, a retrieved snippet, a summary, or a tool description changes what the system does, with no model change at all. lintlang treats these artifacts as code and lints them statically.
Evidence: lintlang
Related terminology
- context engineering
- agent harness
- runtime state
- prompt and instruction configuration
Not the same as
- model weights
- prompt engineering