Articles
Practical writing on running AI agents with a person in charge: what to approve, what to let run, and what to keep on record.

· 11 min read
Human-in-the-loop compared: LangGraph, OpenAI Agents SDK, MCP, Claude Code, Codex
How LangGraph, the OpenAI Agents SDK, MCP, Claude Code and Codex pause an agent for a person, what survives a restart, and when a separate approval service adds something.

· 9 min read
EU AI Act Article 14: human oversight, applied to AI agents
What Article 14 of the EU AI Act asks of high-risk AI systems, when it applies after the Digital Omnibus, and where an approval step fits and falls short.

· 7 min read
OWASP LLM06 Excessive Agency: how an approval gate limits it
OWASP's LLM06:2025 names three causes: too many tools, too much permission, too much autonomy. What an approval gate fixes, and what it leaves to you.

· 7 min read
Risk tiers for AI agent actions: let it run, ask, or never
Four questions for every action an agent can take, the tier each answer points to, fourteen worked examples, and the rule that holds each tier in place.

· 6 min read
Naming agent actions so rules stay manageable
refund.create, deploy.production, email.send_bulk: a naming convention that lets a handful of rules cover an agent, and the mistakes that make rules leak.

· 8 min read
Measuring human-in-the-loop: time to decision, rule coverage and fatigue
Time to decision at the median and 90th percentile, the share settled by rules, expired requests and signs of approval fatigue, with a script to compute them.

· 7 min read
How to add human approval to an AI agent
A working pattern for any agent framework: ask before the risky call, wait for a person, act only on an explicit yes. With code in Python and TypeScript.

· 6 min read
Approve Claude Code and Codex commands from your phone with hooks
A PreToolUse hook makes Claude Code or Codex ask a person before a shell command runs, and answer from a phone. How it works and how to set it up.

· 6 min read
Spending limits for AI agents: caps, budgets and a person above them
An agent that can pay needs limits it cannot talk its way past: a cap per payment, a budget per day or month, and a person for everything above.

· 5 min read
Two-person approval for AI agent actions
Some agent actions are too big for one person's click. How two-person approval works for AI, when to require it, and how to set it up.

· 7 min read
AI agent guardrails: the five controls that matter in production
Permissions, approvals, rules, a kill switch and an audit trail: the five guardrails an AI agent needs, and what each one cannot do alone.

· 6 min read
Human-in-the-loop for AI agents: what to approve and what to let run
Which agent actions deserve a human decision, which can run on a rule, and how to tell them apart.

· 5 min read
Add an approval step to any MCP agent in ten minutes
A step-by-step guide to putting a person's yes between an MCP agent and its risky actions.

· 5 min read
Approval fatigue is real. Standing rules fix it without giving up control
Asking about everything trains people to click yes. Standing rules keep the questions rare and meaningful.

· 5 min read
What an audit trail for AI agents should record
The six facts every agent action should leave behind, and why the vendor's own log is not enough.

· 4 min read
Why every team running agents needs an emergency stop
When an agent goes wrong you need one switch, not a hunt through dashboards. What a good emergency stop does.
