Ask HN: How are you handling real-time data triggers for LLM agents?
Most LLM agents are reactive, they only work when you prompt them. I’m interested in how people are building "proactive" agents that trigger based on external world events (webhooks, sensor data, price changes).
Are you using cron jobs, custom middleware, or something else? I know my setup is pretty dumb and very specific to me, but I am using:
* iPhone 15 Pro
* Shortcuts app to schedule it to run on a timer
* Scriptable to process the returned data
* ChatGPT app as the brain