Ryan Carson and Claire Vo on Managing AI Agents at Scale

X postRyan CarsonAnnouncement

Ryan Carson announced a new episode featuring Claire Vo, focusing on managing concurrent AI agents and creating operational automation workflows.

Key points

  1. Managing and prioritising multiple concurrent AI agents using structured folder systems and analogue planning.
  2. Building and implementing AI-driven operational workflows and automation.
  3. Carson notes using mostly Fusion when asked about model selection in the context of Devin.

Why it matters

As teams run multiple concurrent agents, organizational systems become critical to avoid complexity bottlenecks.

Analysis

Carson and Vo highlight pragmatic approaches to agent orchestration, relying on folder structures and offline planning rather than complex prompt coordination to manage workload.

Original post

Ryan Carson

@ryancarson · 24 August 2026

My 2nd episode with @clairevo is live! You'll learn ... 1. How to manage AI agents at scale Organize, prioritize, and manage multiple concurrent agents using a structured folder system and analog planning 2. How to build AI-driven operational workflows Implement automation

107 likes8 replies95 bookmarks13k views

View on X
More posts in the thread (2)
  1. @EarnWhere @clairevo Thx!
  2. @timanrebel @clairevo Mostly Fusion
Selected replies (5)
  • @EarnWhere @ryancarson @clairevo Easily the most helpful podcast episode I’ve heard in a long time. I appreciate you all pushing the solo building like you have and not gatekeeping it.
  • @timanrebel @ryancarson @clairevo Really nice episode @clairevo and Ryan! ❤️ Love the non-hype energy you two have, just sharing experiences. One question I had, and maybe I missed it in the episode: I’m curious which models you use inside of Devin?
  • @ssharptake @ryancarson @clairevo The folder system for agents is a nice touch Analog planning for digital workers feels right
  • @ikramulweb3 @ryancarson @clairevo Folder system sounds fine, but how are they handling coordination and failure modes across concurrent agents?
  • @ajs6888 @ryancarson @clairevo 多代理一上规模,文件夹和规划比提示词更管用。

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Video

    Video:Greg Isenberg

    Managing Teams of AI Agents: Ryan Carson on Cloud-First Development

    In an interview with Greg Isenberg, Untangle founder and former Treehouse CEO Ryan Carson outlines how knowledge workers are evolving into managers of AI agents. He shares why cloud-hosted VMs replace local environments, how he ships 22 to 40 PRs daily, and the operational automations required to monitor agent behaviour and secure production keys.

    AI & LLMs· Talk

  • Article:Nate

    Agent Maintenance: Why Pruning AI Systems Matters More Than Building Them

    Nate argues that maintaining AI agents will soon be a more critical skill than creating them. Agents continue to generate output long after becoming inaccurate. Citing Vercel's decision to delete 80% of its sales agent's tools to improve results, he outlines how stripping away bloat and maintaining structural harnesses keeps systems reliable.

    AI & LLMs· Opinion

  • X post:Kun Chen

    Orchestrating AI Agents: Combining Herdr and Firstmate

    Kun Chen outlines the architectural combination of Herdr and Firstmate for multi-agent workflows. Herdr manages agent lifecycles and organization, while Firstmate acts as the primary orchestrator and single point of contact.

    1kbookmarks74.6kviews

    AI & LLMs· Tool

  • Video

    Video:LangChain

    Cognition President Russell Kaplan on Coding Agents, Benchmarks, and Model Routing

    In a discussion with Harrison Chase (LangChain), Cognition President Russell Kaplan details the evolution of Devin, the AI software engineer. He explains how common programming tasks are hitting 'intelligence saturation', why mergeability is the new eval benchmark, and how Devin Fusion cuts token costs.

    AI & LLMs· Discussion

  • Video

    Video:CURT

    High-Throughput Agentic Engineering by Ex-Meta Principal Engineer

    Kun, former L8 Principal Engineer at Meta, Microsoft, and Atlassian, demonstrates his high-throughput agentic engineering setup. His open-source tool firstmate allows a single lead agent to orchestrate worker agents across dozens of active repositories.

    AI & LLMs· Demo

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.