Hacker Newsnew | past | comments | ask | show | jobs | submit | allmathl's commentslogin

> At Pig, we built computer-use agents for automating legacy Windows applications (healthcare, lending, manufacturing, etc).

How do you justify this vs fixing the software to enable scripting? That seems both cheaper and easier to achieve and with far higher yields. Assume market rate servicing of course.

Plus; how do you force an "agent" to correct its behavior?


Sorry, am I missing something? They obviously do not control source for these applications, but are able to gain access to whatever benefit the software originally had - reporting, tracking, API, whatever - by automating data entry tasks with AI.

Legacy software is frequently useful but difficult to install and access.


[flagged]


I think if you got some experience in the industries this serves then you'd reconsider your opinion


i don't see how improving the source could detriment anyone. The rest is just relationship details. The decent part about relationship details is imprisonment.


As nawgz said, the applications they are automating are often closed-source binary blobs. They can't enable scripting without some kind of RPA or AI agent.


Correct. In the RPA world, if there's an API available, or even a sqlite server you can tap into, you absolutely should go directly to the source. Emulating human mouse and keyboard is an absolute last resort for getting data across the application boundary, for when those direct apis are unavailable.


Can someone explain how an "agent" is distinct from a "chatbot"?

I'm reading descriptions of agents and it just seems like the same tech deployed with authority to write and a scheduler


Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: