Blog
Writing
Life, tech, and everything in-between.
Guardrails for LLM Agentic Systems: Layered Defense
7 minAI
Safety instructions in a system prompt are not sufficient for production. Benchmark agents still behave unsafely in a significant fraction of cases. The fix is layered defense: prompt-level, tool-level, model-level, and system-level guardrails stacked so any one failure is caught by the next.
Human-in-the-Loop Patterns for LLM Agents
7 minAI
Full autonomy is not the right target for every agent. Put a human in the loop at the points that matter: before dangerous actions, for ambiguous decisions, as an escalation path when the agent is stuck. Checkpointing makes the pauses cheap.