Comment by arjie

2 hours ago

I only have the agent investigate directly. To actually configure the Mikrotik, I have the agent write a script that is aimed to be idempotent and then run the script. Investigation is fine, but the script acts as a memory of intent which I find useful. As agents get better, it can be a textual representation rather than a script, but for now that suffices.

5 comments

arjie

Reply
abound  2 hours ago

> I have the agent write a script that is aimed to be idempotent and then run the script.

You can take this one step further and have the agent write Terraform configs [1]. I did this (including having the agent import all the initial resources from the live device), works great and is generally more robust than a script.

[1] https://github.com/terraform-routeros/terraform-provider-rou...

  • arjie  2 hours ago

    I originally wrote specific terraform providers (even one for just configuring an Ubuntu machine), but over time I found that TF is a bit too heavyweight for my use-cases. The shell script works well because state divergence can be investigated by the LLM. The slowness of state refreshing etc. does make a TF apply painful. For me at least.

dools  1 hour ago

> As agents get better, it can be a textual representation rather than a script, but for now that suffices

I can’t see any reason to have agents do what a script can do. If the operation is deterministic then why pay every time it gets done? This is why MCP seems so pointless to me.

  • arjie  1 hour ago

    It's adaptive and can handle config drift if someone has altered the machine in the meantime between script invocations. Not required if you're disciplined, of course.