AI directory search
Use this when you know the topic you need: Claude Code, MCP, evals, RAG, agents, product, coding, prompting, foundations, or model internals.
2 matches for "evaluation harnesses"
Open security benchmark · Hugging Face Community · Intermediate to advanced
You want a reproducible September 5, 2026 benchmark for comparing how agentic models handle indirect prompt injection, with public data, a public harness, control runs, tool-call traces, and outcome metrics tied to unauthorized payment actions.
agents, prompt injection, agent security, evals, tool use
Evaluation guide · Hugging Face Community · Intermediate
You need a practical evaluation plan built around representative tasks, controlled environments, observable traces, outcome and constraint metrics, repeated trials, and production failures turned into regression tests.
hugging face, agents, evals, evaluation harnesses, trajectory metrics