November 01, 2026
Applied AI: Long-Running and Background Agents
Information in this post reflects publicly available sources as of November 1, 2026. A procurement team gives an agent a job: review 40 vendor contracts, email each vendor to confirm renewal terms, and produce a comparison by morning. Two hours in, at contract 31, the server running the agent restarts for a routine deploy. The run is gone. Someone starts it again, the bill doubles, and 30 vendors receive the same email twice. Nothing about the mod… Read More
by Phee Jay
November 01, 2026
Applied AI: Voice and Realtime Agents
Information in this post reflects publicly available sources as of November 1, 2026. You call a support line and an AI agent answers. You ask a question, and then nothing happens for two seconds. You start to repeat yourself, and at that exact moment the agent starts talking too. Both of you stop. It apologizes and starts again from the beginning, and you are already reaching for the zero key to find a human. The agent behind that call might have t… Read More
by Phee Jay
July 07, 2026
Explained: Agentic AI
It is 11:40 pm and a deploy is blocked by one failing test. You paste the stack trace into a chatbot. It suggests a fix. You copy the fix into your editor, rerun the suite, get a new error, and paste that back. Nine round trips later, the test finally passes. The model did the thinking, but you did everything else: running commands, reading output, deciding whether to keep going. Now picture the same night with a coding agent. You type one senten… Read More
by Phee Jay