<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/why-one-ai-agent-isn-t-enough-and-how-to-run-1-000---cj-avilla-harrison-stall-anthropic-2gk37vhpu" -->

---
title: Why One AI Agent Isn’t Enough (And How to Run 1,000) -...
description: Ken Thompson built Unix in a month. IBM put 1,000 engineers on OS/360. And in 1998, Linus Torvalds hit his limit. Now we're hitting that same wall managing AI...
canonical: https://daily.dev/posts/why-one-ai-agent-isn-t-enough-and-how-to-run-1-000---cj-avilla-harrison-stall-anthropic-2gk37vhpu
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla & Harrison Stall, Anthropic | daily.dev
og:description: Ken Thompson built Unix in a month. IBM put 1,000 engineers on OS/360. And in 1998, Linus Torvalds hit his limit. Now we're hitting that same wall managing AI...
og:url: https://daily.dev/posts/why-one-ai-agent-isn-t-enough-and-how-to-run-1-000---cj-avilla-harrison-stall-anthropic-2gk37vhpu
og:image: https://api.daily.dev/og/posts/2Gk37vHpU.png
og:image:alt: Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla & Harrison Stall, Anthropic
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla & Harrison Stall, Anthropic

**[AI Engineer](https://daily.dev/sources/aidotengineer)** · 101 min read · 0 upvotes · 0 comments

## Summary

Ken Thompson built Unix in a month. IBM put 1,000 engineers on OS/360. And in 1998, Linus Torvalds hit his limit. Now we're hitting that same wall managing AI agents.

Anthropic's CJ Avilla and Harrison Stall introduce Flows in Claude Managed Agents. You hand Claude a goal, and it plans and runs its own multi-agent topology of up to 1,000 agents through the API. In this hands-on workshop they demo a stock watchlist scanner, show how to spend more compute on the phases that matter, walk through the Bug Hunter and Explainer Studio templates, and explain why single agents fail through laziness, self-preference bias and goal drift. They finish with a deep dive on running agents safely at scale: budgets, interrupts, auto mode, credential vaults and network lockdown.

Speakers:
CJ Avilla, Member of Technical Staff, Anthropic
X: https://x.com/cjav_dev

Harrison Stall, Member of Technical Staff, Anthropic
X: https://x.com/HarrisonStall

https://www.anthropic.com

0:00 Unix vs. OS/360: the scaling problem
6:00 Meet CJ & Harrison
7:00 Introducing Flows in Claude Managed Agents
9:05 Why single agents hit a wall
14:00 How dynamic workflows work
17:25 Demo: stock watchlist scanner
23:20 From console to production: tuning each phase
32:15 Q&A, round 1
1:04:45 Bug Hunter: multi-agent PR review
1:07:15 Explainer Studio: flows that make videos
1:12:15 Laziness, self-bias & goal drift
1:15:20 Agent safety at scale
1:20:05 Declare, contain, detect
1:21:15 Separating the brain from the hands
1:27:50 Credential vaults & locking down tools
1:31:45 Wrap-up + Q&A, round 2

Live from the Sheraton New York Times Square Hotel in New York City, AI Engineer New York 2026 is an AI conference for engineers and technical leaders building production AI across banking, hedge funds, fintech, insurance, and asset management.

Event: AI Engineer NYC
Dates: October 12–14, 2026
Venue: Sheraton New York Times Square Hotel

Learn more about the event:
https://ai.engineer/nyc/2026#

Subscribe for more AI Engineer talks, livestreams, and event coverage:
https://www.youtube.com/@aidotengineer

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.youtube.com/watch?v=kiClTcJUnhc>

---

Tags: [#ai](https://daily.dev/tags/ai), [#ai-engineering](https://daily.dev/tags/ai-engineering)

[View this post on daily.dev](https://daily.dev/posts/why-one-ai-agent-isn-t-enough-and-how-to-run-1-000---cj-avilla-harrison-stall-anthropic-2gk37vhpu)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla \u0026 Harrison Stall, Anthropic","url":"https://daily.dev/posts/why-one-ai-agent-isn-t-enough-and-how-to-run-1-000---cj-avilla-harrison-stall-anthropic-2gk37vhpu","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/why-one-ai-agent-isn-t-enough-and-how-to-run-1-000---cj-avilla-harrison-stall-anthropic-2gk37vhpu"},"datePublished":"2026-10-16T19:10:08.692Z","dateModified":"2026-10-16T20:57:17.401Z","description":"Ken Thompson built Unix in a month. IBM put 1,000 engineers on OS/360. And in 1998, Linus Torvalds hit his limit. Now we're hitting that same wall managing AI...","image":"https://i.ytimg.com/vi/kiClTcJUnhc/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/kiClTcJUnhc/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/why-one-ai-agent-isn-t-enough-and-how-to-run-1-000---cj-avilla-harrison-stall-anthropic-2gk37vhpu","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,ai-engineering","timeRequired":"PT101M","video":{"@type":"VideoObject","name":"Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla \u0026 Harrison Stall, Anthropic","description":"Ken Thompson built Unix in a month. IBM put 1,000 engineers on OS/360. And in 1998, Linus Torvalds hit his limit. Now we're hitting that same wall managing AI...","thumbnailUrl":"https://i.ytimg.com/vi/kiClTcJUnhc/sddefault.jpg","uploadDate":"2026-10-16T19:10:08.692Z","duration":"PT101M","url":"https://api.daily.dev/r/2Gk37vHpU","embedUrl":"https://www.youtube.com/embed/kiClTcJUnhc"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"Why One AI Agent Isn’t Enough (And How to Run 1,000) - CJ Avilla \u0026 Harrison Stall, Anthropic"}]}
```

