geokos

It is an interesting solution that you developed with learnings from your personal experience. Appreciate that! Hope this finds its space in the market. Wish you the best!

I agree with both you and matsemann. Getting the requirements right by conducting a cheap POC is a good approach. Matsemann is highlighting the failure that creeps in when the POC is shipped as if it meets the requirements.

Someone has to sign off on the requirements and also what is released. So, two approval steps by a person. The first approval is for a plan and the acceptance criteria. The second approval is a check against the plan. The agents can do all the work of taking the plan, breaking it down into tasks, building, and then verifying it. A good orchestrator will include people in the workflow at the points where their decisions matter and maintain a record of it.

I like to print content from websites and marking/writing on it. It is such a helpful feature to print only the core content. It is a prime example of an obvious need lying in plain sight, and that's ignored. Glad that someone has worked on it.

"Getting it right is more valuable than getting in first" is what I will agree with. I feel what the author is trying to say. The AI field is moving too fast. One day it is prompt engineering. Then it's RAG, MCPs, Loop engineering, and now harness engineering. But rather than fearing that these are becoming obsolete, I feel there is an opportunity to participate by hopping on and sprinting ahead.