Networking with agents: Put them in the right conversations with Tailscale

#1

Post by matsur » Tue, Mar 10, 2026, 6:38 PM UTC

Networking with agents: Put them in the right conversations with Tailscale
blog.firetiger.com

Re: Networking with agents: Put them in the right conversations with Tailscale

#2

Post by Avicebron » Wed, Mar 11, 2026, 12:03 AM UTC

So is inference happening in network or not?

Re: Networking with agents: Put them in the right conversations with Tailscale

#3

Post by mrbluecoat » Wed, Mar 11, 2026, 12:50 AM UTC

Happily handing over all your private data to a shady tiger in a trenchcoat - seems like an apt visual for the current state of AI.

Re: Networking with agents: Put them in the right conversations with Tailscale

#4

Post by data-ottawa » Wed, Mar 11, 2026, 2:14 AM UTC

Avicebron wrote: post #2

So is inference happening in network or not?

No, you're granting firetigre (external) access to your database (internal) via your tailnet.

Re: Networking with agents: Put them in the right conversations with Tailscale

#5

Post by plusplusungood » Wed, Mar 11, 2026, 3:50 AM UTC

I worked for a company once where we ran this dodgy shipping software on prem that integrated with our backend via SQL access. When there was an issue, their techs would rdp to a server and run this little VB app that turned out to be a dialog box that could run arbitrary SQL code against our production database.

I trust that more than this nonsense. WTF are we doing?