When to Use an AI Agent Instead of a Simple LLM Call

Description and use

<p>The word “agent” is being attached to almost every AI feature right now. A prompt calls a model, the model returns JSON, and suddenly the architecture diagram has an agent in it.</p> <p>That label is not harmless. An agent brings a loop, tool access, state, new failure modes, more latency, and a larger surface to evaluate.</p> <p>A useful default is much simpler:</p> <blockquote> <p>Use the least autonomous architecture that can solve the problem reliably.</p> </blockquote> <p>Sometimes that is one LLM call. Sometimes it is a workflow controlled by your code. An agent becomes useful only wh

Problem

<p>The word “agent” is being attached to almost every AI feature right now. A prompt calls a model, the model returns JSON, and suddenly the architecture diagram has an agent in it.</p> <p>That label is not harmless. An agent brings a loop, tool access, state, new failure modes, more latency, and a larger surface to evaluate.</p> <p>A useful default is much simpler:</p> <blockquote> <p>Use the least autonomous architecture that can solve the problem reliably.</p> </blockquote> <p>Sometimes that is one LLM call. Sometimes it is a workflow controlled by your code. An agent becomes useful only wh

Outcome

<p>The word “agent” is being attached to almost every AI feature right now. A prompt calls a model, the model returns JSON, and suddenly the architecture diagram has an agent in it.</p> <p>That label is not harmless. An agent brings a loop, tool access, state, new failure modes, more latency, and a larger surface to evaluate.</p> <p>A useful default is much simpler:</p> <blockquote> <p>Use the least autonomous architecture that can solve the problem reliably.</p> </blockquote> <p>Sometimes that is one LLM call. Sometimes it is a workflow controlled by your code. An agent becomes useful only wh

Evidence

When to Use an AI Agent Instead of a Simple LLM Call

Source