- In short
- Model-based checks use a lightweight classifier or judge model and suit ambiguous intent that cannot be exhaustively enumerated, such as novel jailbreak phrasing or toxicity. Deterministic checks use a rule - a blocklist, regex, schema validator, or allowlist - and suit clearly defined conditions where speed and provability matter. Tool-call authorization should almost always be deterministic so it is auditable and replayable, and the two check types are layered in series so each covers the other's failure mode.
Full concept guide coming soon
We are building the in-depth, exam-aligned guide for this knowledge point. In the meantime, explore the prerequisites and related concepts below, watch the official Anthropic Academy lessons, and start an adaptive study session to master it with Archie.
Watch and learn
Official Anthropic Academy lessons first, then hand-picked walkthroughs. Videos load only when you press play.
No videos curated for this concept yet
We are still curating the best official and community videos for this topic.
References & primary sources
Adaptive study
Master this concept with Archie
Practice it inside an adaptive study session. Archie, your Socratic AI tutor, tracks your mastery with Bayesian Knowledge Tracing and schedules the perfect next review.