LangChain/Advanced
Intermediate9 min

Guardrails

Validate and filter agent inputs and outputs using middleware hooks. Use before_agent for session-level input checks, after_agent for final output safety, and layer deterministic (regex) + model-based (LLM) guardrails for defense in depth.

Quick Reference

  • before_agent — runs once per invocation; use for input blocking and auth checks
  • after_agent — runs once after the loop ends; use for final output safety scanning
  • return {'jump_to': 'end'} — short-circuit the agent immediately from any hook
  • Deterministic guardrails: regex/keywords — fast and cheap
  • Model-based guardrails: LLM classifier — catches semantic violations

Deterministic vs Model-Based

Guardrails fall into two categories. Deterministic guardrails use rule-based logic — regex, keyword matching, schema validation. They're fast and free but can be bypassed with rephrasing. Model-based guardrails use an LLM to evaluate content semantically — they catch nuanced violations but add latency and cost. Layer both for defense in depth.

ApproachStrengthsWeaknesses
Deterministic (regex/keywords)Fast, free, predictable, auditableBypassed by paraphrasing, no semantic understanding
Model-based (LLM classifier)Catches semantic violations, nuancedAdds latency and cost per call