Quick answer

AI Summary: An entertaining and insightful case study detailing the unpredictable failures, infinite loops, and 'autonomous chaos' that occurred when an AI swarm was given control of a marketing agency.

Blog2025-10-05•Source ↗•8 attns449 checkouts

Claim

I Let an Agentic AI Run My Agency for a Week. Here's What Broke.

Authors

Discuss with Grok

Julian Thorne

ABSTRACT

In a bold (and slightly reckless) experiment, Julian Thorne hooked up a LangGraph-powered multi-agent swarm to his digital marketing agency's email, Slack, and ad platforms for a full week. While the agents successfully optimized campaigns and drafted client reports, the experiment revealed the hilarious and expensive friction points of 'Autonomous Chaos.' From agents negotiating against each other to infinite loops of polite email replies, Thorne documents the messy reality of Agentic AI in the wild.

#case-study #agentic-ai/blog/year/2025 #automation #agentic-ai/month/202510 #agentic-ai/blog/month/202510 #agentic-ai/year/2025 #agentic-ai #agentic-ai/blog

Review Snapshot

Explore ratings

4.6

★★★★★

5 ratings

5 star

60%

4 star

40%

3 star

2 star

1 star

Recommendation

100%

recommend this content.

Review this content

Share your opinion to help other learners triage faster.

Write a review

Invite a reviewer

Invite someone by email to share an invited review for I Let an Agentic AI Run My Agency for a Week. Here's What Broke..

Author Inquiries

Public questions about this content. Attendemia will route your question to the author. Vote on the most important ones. No guarantee of response.

Post an inquiry

Sort by: Most helpful