# Elvis Saravia recommends fewer agent touchpoints and a shared queue with memory

> Original title: Decrease the number of touchpoints with agents and instead improve the coordination with and among agents.

- Source: Elvis Saravia
- Published: 2026-11-08T04:08:30.000Z
- Bad Influence: https://badinfluence.news/items/seygm82o61xtk2h1ucqsw1bqb
- Original: https://x.com/omarsar0/status/2119280878362759303

## Summary

Elvis Saravia says teams should reduce direct touchpoints with agents and improve coordination among them. He recommends adding a queue and a memory system, and says he tested this setup in his own harness. He also quotes Brian Armstrong describing a similar workflow with lead agents, sub-agents, a prioritized review queue, and a learned preference model.

## Post

Decrease the number of touchpoints with agents and instead improve the coordination with and among agents.

Add a queue and a good memory system and watch how much faster and efficient you become.

Any other setup from what I have tested in my custom harness will hold back agents powered by frontier models.

I use this setup for coding, researching, strategizing, and much more.

Increasingly, coordination and personalization are the key aspects of a harness that will give you the biggest edge.

## Quoted post @brian_armstrong

> I've changed how I work over the last few weeks.
> 
> I now have one lead agent for each area of focus, running all the time, and a chief of staff agent that oversees them. Each lead manages its own sub-agents that write code, test it, chase reviews, and coordinate with team members.
> 
> Everything I need to decide or review comes into one prioritized queue, a simple local web app. Each product review includes screenshots and a video demo of the feature. I clear the queue in batches, mostly by voice and keyboard shortcuts. The leads also bring back ideas I hadn't considered.
> 
> Working from one queue, instead of switching between dozens of chats, has cut a lot of mental overhead. The system keeps learning my preferences and distilling my judgment into a "Brian brain," so its recommendations and first drafts get better before they reach me. The goal is fewer corrections per change.
> 
> Every change still goes through the same human review and security checks. It is eliminating tasks, not human judgment.
> 
> What an exciting time to push the frontier of productivity, especially as we build the economy for agents (agentic finance). We should all keep pushing in this direction.

https://x.com/brian_armstrong/status/2119112609223827547