concept
active
concept:prompts-harness-artifact

Prompts (Harness Artifact)

Natural-language harness artifacts that encode standing behavioral rules, task policies, and reasoning procedures

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Agent Harness
    associated_with
    The external non-parametric context and infrastructure (prompts, skills, memories, tools) through which an LLM is deployed for task execution

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • Reusable procedural modules packaged as callable harness artifacts that can be invoked by agents during task solving
  • Harness component storing prior observations, facts, task outcomes, and strategies for later retrieval
  • Harness components that expose external services and define how agents discover, invoke, and validate them
  • The capability of a task-solving agent to benefit from updated harnesses during task solving
  • A failure mode where weak-tier models fail to invoke relevant harness artifacts (e.g., skills) during task solving
  • The capability of an evolver model to produce useful persistent harness updates from execution evidence
  • The process of updating the external agent harness from execution evidence while keeping model weights fixed
  • LLM-judge pipeline measuring fraction of skill-loaded trajectories where agent follows loaded skill guidance, using Claude Sonnet 4.6 as judge