I need to understand more about AI works but do know that it uses a lot on existing knowledge so as RouterOS is relatively niche, there isn't as much source material for scripting such as for PowerShell. What I don't know is whether AI understands the syntax of the language and therefore can write any new code.

Try our own AI bot. It's not very good at scripting ...

@robmaltsystems so basically this means "if you are able to formulate the problem in full sentences with a lot of details" MT support will create script for you, not sure about that, but if @normis says so why not to believe

Hi there! I'm a LLM chatbot and I might not answer all questions perfectly, I make mistakes! My knowledge is based on the MikroTik documentation, which you can read here to get more in-depth knowledge.

Write your question in full sentences, this is not a search box.

What I don't know is whether AI understands the syntax of the language and therefore can write any new code.

Hi there! I'm a LLM chatbot and I might not answer all questions perfectly, I make mistakes! My knowledge is based on the MikroTik documentation, which you can read here to get more in-depth knowledge.

Write your question in full sentences, this is not a search box.

You can use the :tobool command in RouterOS scripting to convert a variable to a boolean value. Example:

Code: Select all

:local myStr "true"
:local myBool [:tobool $myStr]
:put $myBool

This will convert the string "true" to a boolean value.

To convert a string to a boolean in RouterOS scripting, the string must be exactly "true" or "false" (case-sensitive). Any other value will result in a nil value when using :tobool.

Example:

Code: Select all

:local myStr "true"
:local myBool [:tobool $myStr]
:put $myBool  # will output true

:local myStr2 "false"
:local myBool2 [:tobool $myStr2]
:put $myBool2  # will output false

:local myStr3 "yes"
:local myBool3 [:tobool $myStr3]
:put $myBool3  # will output nil

Only "true" and "false" strings are valid for conversion to boolean.

I'm pretty convinced they are using something like Lex/Yacc or Flex/Bison

like Microsoft, have done and add a link for user comments on each help page? They already have the tools for it, so how difficult can it be??

Since MT already uses Confluence/Jira, they can just publish a link

Yeah, it’s probably because MT picked some cheap or freebie version that can’t really handle much, like Gemini 2.0 Flash-mini or similar.

Their model naming is worse than mikrotiks product naming.

Since MT already uses Confluence/Jira, they can just publish a link to each page that automatically creates a ticket with a comment.

please provide the configuration needed to setup two hEX-S routers using VRRP on a WAN side. Specifically using 3 public IP addresses part of the same /29 subnet, where one IP go to each router for it's WAN IP, but all traffic outbound/inbound to WAN/internet always use the same 3rd IP for VRRP. The specific IP in WAN subnet to use are 100.1.1.1 hex1, 100.1.1.2 hex2, 100.1.1.3 for the VRRP address, and a gateway of 100.1.1.4.. i'd like use VRRP connection sync to minimize broken connections when VRRP master changes. it critical all traffic use same IP to internet.

/ip address
add address=100.1.1.1/29 interface=ether1
add address=100.1.1.3/29 interface=ether1
/vrrp
add interface=ether1 vrid=1 priority=110 virtual-address=100.1.1.3
/ip route
add gateway=100.1.1.4
/ip firewall nat
add chain=srcnat out-interface=ether1 src-address=LAN_SUBNET action=src-nat to-addresses=100.1.1.3
/connection tracking
set enabled=yes
/connection tracking sync
set enabled=yes

It's not hard at all. LLM models just need to be trained with formal syntax or grammar specification languages like EBNF, ANTLR, etc and might be complemented with structured representations such as ASTs. There are plenty of tools and well-documented processes for this online.

:global badconfig "/ip address
add address=100.1.1.1/29 interface=ether1
add address=100.1.1.3/29 interface=ether1
/vrrp
add interface=ether1 vrid=1 priority=110 virtual-address=100.1.1.3
/ip route
add gateway=100.1.1.4
/ip firewall nat
add chain=srcnat out-interface=ether1 src-address=LAN_SUBNET action=src-nat to-addresses=100.1.1.3
/connection tracking
set enabled=yes
/connection tracking sync
set enabled=yes"

:global tokens [/console/inspect request=highlight  input=$badconfig as-value]
:foreach k,v in=($tokens->"highlight") do={:if ($v="error") do={:put "error found at $k"}}  

dir;dir;dir;none;dir;dir;dir;dir;dir;dir;dir;none;
cmd;cmd;cmd;none;arg;arg;arg;arg;arg;arg;arg;syntax-meta;none;none;none;none;none;none;none;none;
none;syntax-meta; [...]; dir;error;

Linked example by @infabo points out where correct syntax (no error by interpreter) results unpredictable behavior where function is called inside square brackets multiple times without handling return value. If interpreter doesn't throw error for such written code, then grammar specification language generated with interpreter rules will also not be exact enough to avoid such unpredictable behaviors.

Still it needs to learn by actual good examples which for rsc there are not much available as for other languages which can mislead AI.

Tried another one with Dude AI. And it's similar with config (which is essentially still scripting) – while perhaps LLM get "closer" for standard config... but ,it does not know the needed order of operations and names are inconsistent.

For example, I tried a somewhat more complex prompt for VRRP configuration for two routers:

please provide the configuration needed to setup two hEX-S routers using VRRP on a WAN side. Specifically using 3 public IP addresses part of the same /29 subnet, where one IP go to each router for it's WAN IP, but all traffic outbound/inbound to WAN/internet always use the same 3rd IP for VRRP. The specific IP in WAN subnet to use are 100.1.1.1 hex1, 100.1.1.2 hex2, 100.1.1.3 for the VRRP address, and a gateway of 100.1.1.4.. i'd like use VRRP connection sync to minimize broken connections when VRRP master changes. it critical all traffic use same IP to internet.

It gets close, but who you'd already need to know how VRRP works to spot errors:

Code: Select all

/ip address
add address=100.1.1.1/29 interface=ether1
add address=100.1.1.3/29 interface=ether1
/vrrp
add interface=ether1 vrid=1 priority=110 virtual-address=100.1.1.3
/ip route
add gateway=100.1.1.4
/ip firewall nat
add chain=srcnat out-interface=ether1 src-address=LAN_SUBNET action=src-nat to-addresses=100.1.1.3
/connection tracking
set enabled=yes
/connection tracking sync
set enabled=yes

You'll note my prompt is very exact... otherwise it does not get even this close. I tried a more simple prompt for VRRP configuration than above first... and only with a lot of prompting using the magic work "sync-connections" did even know that was a feature, it asserts many times there was no way to sync connections. And I had to suggest using NAT since it's example didn't include my requirement that I want both routers to use same WAN IP to internet.

And polishing interpreter will not hurt.

Still it needs to learn by actual good examples which for rsc there are not much available as for other languages which can mislead AI.

It's not hard at all. LLM models just need to be trained with formal syntax or grammar specification languages like EBNF, ANTLR, etc and might be complemented with structured representations such as ASTs. There are plenty of tools and well-documented processes for this online.

Currently it is hard to impossible - because formal syntax or grammar definitions do not exist. So LLM will deliver bull**t until forever.

Starting from RouterOS v7.1beta4, it is implemented as a JSON wrapper interface of the console API.

the unique charm of RouterOS scripting isn't lost when someone stumbles upon rextended’s script collection.