I gave my local LLM one job that runs every night, and it's done more for me than a year of chatting with it
It's been far more useful ever since
After years of experimenting with local LLMs, the author found a surprisingly useful application for one of them. Instead of asking the model to do everything a cloud-based version could, the author decided to give it a simple, recurring task. The model uses n8n and Qwen 3.5 9B to check the author's emails, Asana tasks, and messages for unfinished commitments, missed follow-ups, and other items needing attention.
Every night, the model prioritizes these items and sends the author a brief over email in the morning. This workflow helped the author keep track of everything they had committed to doing, which had been a constant struggle. The author found local LLMs to be more useful when given smaller, well-defined tasks, rather than expecting them to handle complex projects.
Written by urgent.news from XDA Developers's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
