This... does not seem like separation of concerns.

Not to mention that the data layer seems like the one where you want to keep things most deterministic.

If you really want to run an agent on each created row, you could run this in a replica and stream the replies back to your system of record.

noupdates 3 hours ago | parent | prev [-]

To decouple this the person would have to broadcast nearly every event and rebuild the observer layers elsewhere.

	▲	nkmnz an hour ago \| parent \| next [-]
		You could replicate and separate your llm-postgres from the system-of-record-postgres.
	▲	thatwasunusual an hour ago \| parent \| prev [-]
		And IMO that's what should be done. Don't get me wrong, I like the idea and all that, but this is another pgsql "solution" that is tied to the database layer, when it should be in the application layer. I like to be database agnostic, and while I prefer PostgreSQL on production, I prefer SQLite on the dev layer. You should never have to HAVE TO use a specific database to make your APPLICATION work.