DEV Community

PawBot - An AI Desktop Puppy That Eats Your Files 🐾

Varshith V Hegde on August 15, 2026

This is a submission for Weekend Challenge: Dog Days Edition What I Built Remember Neko the cat and those Tamagotchi desktop pets from ...

Read full post

Anik Sikder • Aug 17

What stood out to me isn't the Gemini integration it's the product thinking behind it. The puppy already has personality through animations, behaviors, moods, hunger, sleep cycles, and interactions. AI simply adds another layer of expression.

Too many projects start with "Where can I put AI?" This one starts with a fun product and uses AI where it actually adds value. That's usually the stronger design approach.

Tom Jones • Aug 16

The eat interaction is the part I would protect. It works because a bark from a filename is obviously a joke, and nobody reads "Mmm, crunchy homework!" as a claim about what was in the PDF.

We hit the failure mode that sits one step past that. Our own pipeline summarised dev.to threads, and its prompt was assembled from a title, a URL and the comment thread. The article body was never in it, for the entire life of the file. On long posts with active threads the summaries looked fine. On an 85 word promo post with no comments the prompt collapsed to a bare title, and the model returned about 100 words of specific methodology that existed nowhere, naming metrics the article never mentioned. Nothing errored and nothing logged. We posted a public comment built on one before anyone checked.

The tell turned out to be arithmetic rather than judgement. The invented summaries were roughly as long as their sources or longer; the honest ones were under half. Nothing lived in between, so a word count caught what reading had not.

So the thing I would write down now, while the design is fresh: be explicit about what actually reaches Gemini when the pup eats something. If it is the filename and the MIME type, the barks stay charming forever and the joke is safe. If someone later pipes in extracted text, the same code path starts making claims about contents, and it will do that just as confidently on the file it failed to parse.

Lovely build. The state machine diagram is doing a lot of work in that post.