how to scale AI agents in production workflows when the underlying business process is broken?
Summary
A practitioner shares challenges scaling multi-agent AI systems in production, including dealing with shadow workflows (undocumented Slack threads and spreadsheets), context loss across different systems (ERP to CRM), and cross-departmental ownership issues. They seek advice from others who have navigated these real-world problems.
Similar Articles
Has anyone deployed a multi-agent AI employee in production?
A discussion about deploying multi-agent AI systems in production, where different agents handle planning, execution, communication, and project management, asking about real-world experiences and bottlenecks.
Running AI agents in production at scale — what pain are you hitting, and what's actually working?
A discussion on the challenges and successful strategies for deploying AI agents in production at scale, covering common pain points and effective solutions.
Where AI agents actually break in real workflows (not demos)
A discussion on where AI agents fail in real workflows, highlighting issues with coordination, reliability under messy inputs, and the challenge of reducing human intervention in production.
What broke first when you went from one AI agent to several?
A discussion on the operational challenges that arise when scaling from one AI agent to multiple, including context handoff, auth permissions, duplicated work, and cost tracking.
The first AI agent is easy. The fifth is where companies get into trouble.
The article discusses the operational challenges companies encounter when scaling from a few AI agents to dozens, proposing a solution that separates business logic from technical control to manage agentic workflows effectively.