---
title: "Comment by Kartik N V J K on \"I'm Building An AI Agent. Except I'm Not. And Neither Are Most Of Them.\" | Hashnode"
description: "I respect the honesty of admitting B.E.N.N.Y. is mostly if-else logic on top of an LLM layer, because that describes most of what ships as an \"agent\" right now."
url: "https://hashnode.com/posts/i-m-building-an-ai-agent-except-i-m-not-and-neither-are-most-of-them/6a4e4310037de99e932cac70/comment/6a4e867063ea2186b13aca14"
---

[Discussion](https://hashnode.com/posts/i-m-building-an-ai-agent-except-i-m-not-and-neither-are-most-of-them/6a4e4310037de99e932cac70)

Comment [I'm Building An AI Agent. Except I'm Not. And Neither Are Most Of Them.](https://hashnode.com/posts/i-m-building-an-ai-agent-except-i-m-not-and-neither-are-most-of-them/6a4e4310037de99e932cac70)

[Kartik N V J K](https://hashnode.com/@kartik-nvj)

[Jul 8](https://hashnode.com/posts/i-m-building-an-ai-agent-except-i-m-not-and-neither-are-most-of-them/6a4e4310037de99e932cac70/comment/6a4e867063ea2186b13aca14)

I respect the honesty of admitting B.E.N.N.Y. is mostly if-else logic on top of an LLM layer, because that describes most of what ships as an "agent" right now. The line I would draw is autonomy over control flow: if the branching lives in your code rather than in the model's decisions, it is orchestration, which is often the safer choice anyway. Given your human-review step before a lead is submitted, do you actually want B.E.N.N.Y. choosing the next action on its own, or is the deterministic path exactly what a business-critical flow needs?

[Ruben Arevalo](https://hashnode.com/@rchrisarevalo)

[Jul 11](https://hashnode.com/posts/i-m-building-an-ai-agent-except-i-m-not-and-neither-are-most-of-them/6a4e4310037de99e932cac70/comment/6a4e867063ea2186b13aca14#reply-6a5203ae189fd73dd7a8ac37)

Hi Kartik! For B.E.N.N.Y. I would apply a deterministic approach in this case. I don't want it to make decisions to qualify leads on its own because the last thing I want are false positives, false negatives, etc. Even though I heavily emphasize the importance of human-in-the-loop (HITL) architecture, I am open to exploring more automation and agentic behavior of other aspects of B.E.N.N.Y., such as the timesheet monitoring feature I mentioned in the article, so that it can catch irregularities or anomalies that a human wouldn't normally catch before turning it over to them.