Skip to content

Instantly share code, notes, and snippets.

@quantra-go-algo

quantra-go-algo/step_7_hard_guardrails_when_the_llm_isn__2.py

Created June 24, 2026 01:29
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save quantra-go-algo/ad5479a3ee3bd219bcea7ea1f41e8f5b to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save quantra-go-algo/ad5479a3ee3bd219bcea7ea1f41e8f5b to your computer and use it in GitHub Desktop.
Download ZIP
guardrailed-llm-agent — Step 7: Hard Guardrails: When the LLM Isn't Enough (snippet 2)
Raw
step_7_hard_guardrails_when_the_llm_isn__2.py
# A4: re-optimize guardrails every month (OPT_FREQ_MONTHS=1)
if best_guard is None or ((m.month - 1) % OPT_FREQ_MONTHS == 0):
best_guard = optimize_guardrails(train, policy)
print('Re-opt guardrails @', m.date(), '->', best_guard)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment