agent

I think you are describing Xata Agent :) https://github.com/xataio/agent It watches metrics/logs, queries pg_stat_stetements for slow queries, the sends slack notification with suggestions, including indexes, but can be more varied than that.

This is great, I like in particular that there are extensions plugins. I’ll be looking at integrating this in the Xata Agent (https://github.com/xataio/agent) as custom tooling.

Check out also https://github.com/xataio/agent which builds on this idea in the form of a dedicated agent for Postgres. Disclaimer: I’ve worked on this project.

The prompts that do most of the work are in this file: https://github.com/xataio/agent/blob/main/apps/dbagent/src/l... - strings stored in these variables: SLOW_QUERIES_PLAYBOOK GENERAL_MONITORING_PLAYBOOK TUNING_PLAYBOOK INVESTIGATE_HIGH_CPU_USAGE_PLAYBOOK INVESTIGATE_HIGH_CONNECTION_COUNT_PLAYBOOK INVESTIGATE_LOW_MEMORY_PLAYBOOK Looks like they are orchestrated by these system prompts: https://github.com/xataio/agent/blob/69329cede85d4bc920558c0...

Interesting, might try it out at home. Documentation asserts: > I use preset SQL commands. I will never run destructive (even potentially destructive) commands against your database. This is enforced by taking the responsibility for generating SQL in order to evaluate state out of the hands of the LLM. The LLM simply interprets results of predetermined commands based on a set of prompts/playbooks: https://github.com/xataio/agent/blob/69329cede85d4bc920558c0...