The Greenhouse and the Lens: Two Modes of Agentic AI Work
I explore two distinct approaches to using agentic AI: the Greenhouse mode for chaotic exploration when goals are unclear, and the Lens mode for focused execution on known targets. Frustration often arises from applying the wrong tool to the job. True expertise lies in recognizing which mode your work requires and using domain knowledge to spot drift, ensuring you stay aligned with your actual objectives.
The scarce asset in an agentic world is a verified mental model of the domain, like an oracle that tells a right answer from a plausible wrong one.
- toplinesoftsys
There is a third mode that requires combination of greenhouse and lens modes, and I did not see AI that is every remotely good working at that third mode. Unfortunately, many real applications are actually require the third mode, and I suspect this is one of key reasons why adoption of AI is so low.
- cadamsdotcom
Sometimes you have a goal & clarity about what you want; others you're just exploring.
Just as non-assisted work: an undisciplined mind will wander. But when there's also an assistant, you're prone to having the wandering done for you.
- afry1
> These tools came about because the cost of trying things out has dropped to nearly zero.
What an obscenely disconnected and privileged notion. "Nearly zero" still currently equates to thousands of dollars of subscription expense per year that normal, workaday people can't afford.
Not to mention the fact that even at this untenable "introductory" level of expense, you're really burning hundreds of thousands of dollars of tokens to do, what was that again?
"Just let the LLM run wild for a while and see what come out the other end?"
"Generate ten solutions to one targeted problem and throw nine of them away because this garbage technology still can't get it right on even the 9th try?"
No wonder the rich bastards of the world love this stuff so much. It encourages so much wanton, indiscriminate, pointless waste in its users.