Create an Agent Builder eval

Use the shared Instance AI eval harness. Agent cases use an Agent-specific authoring directory, dataset, and LangTracer suite.

Required LangTracer preflight

Run this check before sourcing, drafting, or writing an eval. Run it from packages/@n8n/instance-ai:

pnpm exec dotenvx run -f ../../../.env.local -- \
  sh -c 'test -n "${LANGTRACER_URL:-}" && test -n "${LANGTRACER_API_KEY:-}"'

If the check fails, stop before creating an eval file. Ask the user to: