Editing Blog/2025-12-01/Grounding Your Agent (section)

== Grounding ==

The typical approach at this point with an LLM is to provide it grounding information so that it can verify how well the final result is. In this case, I had it write a <code>check_mesh.py</code> file that could verify if the volume was well-formed by whatever criteria we cared about and then let it have the run of the house. Early LLM agents would go around modifying the test file, but by now they've gotten quite good and with this grounding, codex running <code>gpt-5.1-codex-max</code> was able to produce a workable model that didn't have any of the odd self-intersection problems and so on.

I'm pretty early into trying out 3-D printing things for our own convenience, so I'm hoping to find better ways to build these things as time goes by, but one thing that's nice to see is that the classical approach worked:

# Have an LLM write a check program
# Have the LLM work on the problem until the check program passes

It's pretty trivial, and practically everyone does this these days, but it's magical when it works across so many different fields.


{{#seo:|description=The blog post discusses the author's experience using Bambu Studio to create a custom mount for their Eufy E21 baby monitor, including the challenges of}}

[[Category:AI]]
[[Category:Tips]]
[[Category:Blog]]