:alphabet-white-question: Any tools aimed at runni...

# ai

[darkmoon_uk]

alphabet white question Any tools aimed at running an LLM processing prompt over multiple files in a more formal fashion?

I've been having a frustrating time trying to get Agentic AI to perform 'simple' batch-processing tasks.

Example: Getting an AI to take on the job of cleaning up unwanted comments, improve a few simple code cleanliness issues that are just a cut above what IDE reformatting can do.

Each AI solution I've tried so far:
• Warp AI (Best so far despite being aimed at command line, required much manual intervention to approve changes, eventually gave up)
• Junie ('Plans' to do all files but gives up easily after a couple no matter how much you implore it to do all)
• Block Goose (Hopeless, dumb as a sack of bricks at nearly every task asked of it)
...the common theme is that many current agents are really poor at completing batches of changes even when it's an ostensibly simple loop over a few files.
Feeling like building something, but this must be a solved problem(?)

[Ayfri]

Firebend is pretty cool and free with Claude 3.7

[darkmoon_uk]

Thanks @Ayfri; I haven't tried Firebend specifically but all these agents seem to suffer the same problem when faced with a few dozen files or more: They just can't retain the original context and get lost.

So, I threw this together in a few hours: Batch LLM

It cleaned up the files from my original use-case nicely; using Mistral Small model running locally on an M4 Studio Mac. More testing and refinement tomorrow!