letting the LLM decide what action to take

splitting a big task into several smaller subtasks with JSON for the LLM

outputting JSON (instead of text) as a response to a prompt

using the output from an LLM for another prompt (and so on)

a bare-bones ChatGPT (or chatbot wrapper) on your own computer

the former still has predetermined steps while the latter has more autonomy

listing the different kinds of digital assistants

listing the life-cycle of data through agents

coding (and living) mindfully in the age of artificial intelligence

making queries to systems with natural language

pulling up with older words that sound more "rooted"

keying in some words to understand them better