"Agentic engineering" were always just FADs to bring in more revenue for token providers.

If I think an LLM is good for something I create well defined, very deterministic "middleware" for that purpose on top of Openrouter.

k__ 7 hours ago | parent | next [-]

Agentic engineers can build well defined, very deterministic middleware on top of OpenRouter.

Anthropic even says, that an agent based solution should only be your last resort and that most problems are well served with a one-shot.

	▲	ai_fry_ur_brain 6 hours ago \| parent [-]
		Written 1.5 years ago. Anthropic would not advertise this stance today. I'm much more agreeable with that type of LLM workflow. Running "agents" with monolithic "harness" for long time horizon tasks seems wasteful, unecessary but probably super appealing to lazy people.

It’s not a fad or without value.

Its very much valuable to lazy people who dont care about quality or doing hard things. I totally see the appeal for those people.

	▲	wahnfrieden 6 hours ago \| parent [-]
		Sounds like you are more interested in performativity / aesthetics of production if you think writing software in a harder way is an indisputable virtue just because it requires more effort. On top of that you are an elitist about it Agent use can be used to improve quality and maintainability