seldon-experimentsChoose and run the right kind of Seldon experiment — QA baselines, persona usability experiments, or messaging/copy tests. Use when the user wants to test a flow with real personas, find usability friction, ask "why do users drop off", compare copy variants or headlines, or does not yet know which e
seldon-qaAuthor, run and iterate on Seldon QA baselines — a seldon.yml of plain-English test cases run by AI agents against a live URL. Use when the user wants end-to-end QA, regression testing, "test my app", "does the signup flow still work", writing or fixing a seldon.yml, or reading a QA report to fix wh
seldon-resultsRead and act on Seldon experiment results — the narrative summary, findings and severities, per-persona breakdown, coverage caveats, QA verdicts, and messaging scoreboards. Use when an experiment has finished and the user wants to know what was learned, what to fix first, or wants evidence for a spe