Blog
Guides and tutorials on AI agent governance, human-in-the-loop approval, and building safe agentic systems in production.
HTTP 402: the status code that was ahead of its time
The web's payment infrastructure was designed for humans with credit cards. AI agents don't have credit cards. x402 is the protocol that fixes this — and Cloudflare's new Monetization Gateway is a signal that the industry is catching up.
Read moreBuilding a LangChain agent with runtime guardrails: a complete walkthrough
A step-by-step guide to building a LangChain customer support agent and hardening it for production — adding policy enforcement so it can't issue unauthorized refunds, email the wrong recipients, or take irreversible actions without human approval.
Read moreThe production AI agent stack: tools and infrastructure you actually need
Getting an AI agent to work in a notebook takes an afternoon. Getting it to work reliably in production — with real users, real money, and real consequences — takes a different category of tooling. Here's a practical map of the full stack: frameworks, memory, observability, safety, and infrastructure.
Read moreWhy prompt guardrails aren't enough: the case for runtime enforcement
Every major AI safety approach today operates at the text layer: filters, classifiers, system prompts, constitutional rules. None of them touch the thing that actually causes damage, which is the tool call. Here's why that gap matters, and what runtime enforcement does differently.
Read more