Blog · English

Writing about a language for agents

Benchmarks, design decisions and how-tos: automatic HTTPS, installable apps, agentic servers, capability security. Every post is also Markdown — add .md to its URL.

1 results for human-in-the-loop

• September 2, 2026

  Human-in-the-loop for AI agents — approve, confirm and ask are language primitives

  A gate that waits for a real person — in the terminal, or queued behind one-time links when the program runs as a server — and denies when nobody is there. An agent cannot fake an approval.

  • human-in-the-loop
  • agents
  • security

RSS · llms.txt