Joshua Ebner observes that many people default to thinking every business workflow needs an LLM, an agent, or an agentic approach — but argues this is often the wrong mindset. He begins sharing an anecdote from students in his AI engineering course who came to him with a similar assumption, suggesting the full thread likely explores when simpler or more traditional solutions are more appropriate than reaching for cutting-edge AI tooling.

The post highlights a growing tendency in the AI space to over-engineer solutions with large language models and agentic architectures when the problem may not warrant that level of complexity. Ebner's perspective serves as a reminder for engineers and product builders to critically evaluate whether AI is truly the right fit before defaulting to it.

Jerry Liu announces that his full talk from the AI Engineer World Fair is now available on YouTube. The presentation focuses on building AI agents that actually automate knowledge work, breaking down the concept of "knowledge automation" and what it means in practice. Liu emphasizes examining real-world workflows rather than targeting any specific company, suggesting a broader look at how AI agents can transform routine knowledge-based tasks across industries.