architecture

4 articles tagged architecture.

Three thin lines converging from the left on one solid circle, the middle line in burnt orange, drawn as the three triggers that can start an unattended agent run

Always-On AI Agents: Who Approves the Run at 3am?

An always-on AI agent starts its own runs, on a schedule or an event. That moves approval from the run to the setup. What to check before you wire one up.

agents taxonomy10 min read

A single tall rounded rectangle outlined in orange standing on a thin horizontal line, alone on a black ground

Is Claude Code Auto Mode Safe? What the Classifier Misses

Claude Code auto mode blocked 89% of dangerous commands testers missed. Anthropic's own docs say the classifier never reads tool output. That gap is the answer.

agents security11 min read

A bar chart on a black ground where two short outlined bars mark the provider outages and a taller solid orange bar marks the agent tool's longer degraded window

AI Outage September 2026: ChatGPT, Claude and Grok

ChatGPT, Claude and Grok all broke on September 3, 2026. A UTC timeline from four status pages, and why Cursor stayed degraded longer than any lab it runs on.

agents architecture9 min read

A tool call leaving a model loop, crossing an MCP client, and arriving at an MCP server over JSON-RPC

MCP vs Function Calling: Which One Do You Actually Need?

MCP vs function calling: they are not competitors. Function calling is how a model picks a tool. MCP is how a tool reaches any client. One rule tells you which you need.

mcp tool-calling8 min read