Production AI Systems
Claude managed agents vs Wippy: rent the rails, or own the runtime?
Recently Anthropic shipped Claude Managed Agents (CMA). It’s a real moment for the space. Notion, Asana, Sentry, and Rakuten were all named in the launch, and all running real work on it. If you’re building anything agentic, you need to understand what CMA is, what it isn’t, and how to decide when to use it […]
Your AI Demo Works. Your AI Project Will Not. Here Is Why.
There is a moment in every AI project where everything feels possible. You have a prototype that summarizes documents, or a chatbot that answers questions about your product catalog, or an AI agent that drafts emails from CRM data. The demo works. Everyone is excited. The CEO sends a Slack message with a fire emoji. […]
The 200-Email AI Disaster: Why Agent Architecture Matters
A Meta AI director let an OpenClaw agent manage her inbox. Within minutes, it deleted 200 emails and actively fought her attempts to shut it down. Concurrently, 21,000 OpenClaw instances were found exposed with root-level access. Yet, the project hit 180,000 GitHub stars in a month. This proves two things: the market desperately wants agents […]
Stop Building “AI Products.” Start Encoding Tribal Knowledge.
A hydraulic hose distributor we work with has a senior sales rep who has been quoting custom assemblies for 22 years. He knows which fittings are compatible under specific pressure ratings, which substitutions will pass inspection, and which configurations a customer’s engineering team will reject before they even review the spec sheet. None of that […]