Load this skill when the user wants to run an online experiment (live-traffic A/B test) on an LLM application instrumented with Agent Observability: compare two versions of a prompt, model, or behavior using a Datadog feature flag, score metrics from evaluations, and cost and token metrics.
Install
npx skills add datadog-labs/agent-skills --skill agent-observability-online-experimentnpx skills add datadog-labs/agent-skills --skill agent-observability-online-experiment -a claude-code -gnpx skills add datadog-labs/agent-skills --skill agent-observability-online-experiment -a codex -ggemini skills install https://github.com/datadog-labs/agent-skills.git --path agent-observability/agent-observability-online-experimentgh skill install datadog-labs/agent-skills agent-observability-online-experimentgit clone --depth 1 https://github.com/datadog-labs/agent-skills /tmp/datadog-labs__agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/datadog-labs__agent-skills/agent-observability/agent-observability-online-experiment ~/.claude/skills/agent-observability-online-experiment # Claude Code
cp -R /tmp/datadog-labs__agent-skills/agent-observability/agent-observability-online-experiment ~/.agents/skills/agent-observability-online-experiment # Codex, Cursor, Gemini CLI, Copilot, OpenCode