Why Does Claude Code Keep Asking for Permission?
Claude Code asks because Manual mode gates edits, shell commands and web requests. The fixes, safest first: modes, allow rules, sandboxing, then bypass.
Guides
Read →
Tag
#Guardrails
6 posts tagged Guardrails.
Loop Engineering: Designing Agent Loops That Converge
Everyone engineers the prompt; almost nobody engineers the loop around it. Stop conditions, drain loops, retry with backoff, compaction cycles, breaker escalation, budgets, and human gates — the outer-loop mechanics that make an agent converge instead of run away.
Concepts
Read →
MCP Tool Poisoning: How to Secure the Model Context Protocol
How the Model Context Protocol gets attacked — tool poisoning, rug pulls, command injection — and the layered defenses that secure your MCP tools.
Guides
Read →
Running AI Agents Safely: Permission Modes and Sandboxing
How to run autonomous AI agents safely: permission modes and the bypassPermissions foot-gun, workspace isolation, and what to gate vs. allow.
Guides
Read →
Evaluating AI Agent Reliability: How to Measure What You Can Trust
How to measure whether an AI agent is reliable enough to trust: reliability thresholds, why benchmarks overstate, and evaluating on your own codebase.
Guides
Read →
Human-in-the-Loop AI Agents: Approvals That Don't Slow You Down
Design human-in-the-loop AI agents that stay autonomous: an approvals queue that escalates only spend, destructive ops, and scope changes.
Orchestration
Read →