The Guardrail Builder
Write the check that would have caught it. Then test it.
most AI-safety content tells learners guardrails matter; this makes them build one and watch it fail against a fluent-but-wrong sample — the gap between 'I wrote a check' and 'my check actually catches things' is the reveal
What goes in, what comes out
Learner picks a failure scenario from the war-room library and authors a guardrail — a schema check, a least-privilege tool scope, or a pass/fail rubric line — in a structured builder. The tool then fires a battery of good, bad, and adversarially plausible-wrong sample outputs at the learner's own guardrail and scores whether it actually catches what it claims to.
write or configure one guardrail/rubric line, then click 'stress-test it'
a pass/fail readout per sample — caught the bad one, wrongly flagged the good one, or let fluent-but-wrong slip through — plus a robustness score
guardrail type (schema/tool-scope/eval-rubric), difficulty scaling L1-L3, 'attack my own rubric' adversarial mode
FREE, top-of-funnel — /playgrounds gallery; the same mechanic is reused inside Agent Builder, MCP Playground, and Evals Runner labs at L1-L3
Concepts click when you open the machinery.
Three labs are already live and free — the same hands-on style this playground brings to its module.