After building AI agents for a year, I've started believing most businesses don't actually want agents.
Summary
After a year of building AI agents, the author argues that businesses don't actually want autonomous agents—they want specific outcomes like reduced support tickets and manual work, and simpler, reliable solutions often deliver more value than highly autonomous systems.
Similar Articles
I’ve been building AI agents for businesses recently and I think most people are overestimating autonomy and underestimating reliability.
The author argues that in enterprise AI agent development, operational reliability and stability are more critical than high autonomy, advocating for controlled intelligence over fully autonomous systems.
Stop building AI agents.
The author argues that most founders requesting AI agents actually need straightforward automations with minimal LLM integration, citing production failures, compliance hurdles, and higher ROI from simpler workflows. The piece provides a practical decision framework to help builders and founders prioritize reliable automations over complex, unpredictable agents.
Autonomous agents are overrated until the business is readable
The author argues that autonomous AI agents are overrated without structured business context and scoped jobs, sharing practical insights from client work where agents run on fixed cadences with human oversight on writes.
For those building AI agents: what would you actually want an agent to do for you?
The author, working in conversational AI and AI agents, asks builders and users what specific tasks they would want an AI agent to handle in their businesses, emphasizing the value of agents that excel at solving single painful problems.
built 40+ ai workflows for clients this year... 90% of "agents" are gimmicks tbh
The author criticizes the hype around autonomous AI agents, stating they are often ineffective, and recommends building practical, hardcoded AI workflows using tools like n8n and Claude Sonnet for real-world applications.