Guardrails and Safety for Client-Facing AI — Study Resources & PYQs
Curated resources, past papers and PYQs for Guardrails and Safety for Client-Facing AI.
Study resources
- Guardrails Documentation (Article) — Anthropic's own official guidance on reducing hallucinations and adding guardrails to LLM applications.
- AI Safety and Guardrails Explained (Video) — A practical discussion of the safety considerations in deploying AI features to real users.