Oluwatosin Oladayo Aramide

Part 3 of the Agentic NOC series. The smallest real A2A agent: one skill, an Agent Card served at the well-known URL, and the actual message/send JSON-RPC captured live. The horizontal axis, one agent discovering and delegating to another, built from scratch, and how it composes with MCP.

Part 2 of the Agentic NOC series. The smallest real MCP server: one read-only tool, stdio transport, and the actual JSON-RPC handshake captured from a live run. Reproducible with one dependency. This is the vertical axis, an agent reaching a tool, built from scratch.

Anycast usually lets the network decide which datacenter answers. I moved that decision onto two GoBGP hosts that watch both datacenters and steer a single global VIP between them. Here's the design, the traffic flow, and three failover drills that came through with zero failed requests.

Part 1 of the Agentic NOC series. It introduces the two protocols that let AI agents reach tools and each other, MCP (the vertical axis) and A2A (the horizontal axis), and the third, ACP, that converged into A2A, plus the mental model the whole series is built on.

One HTTPS request followed from an external client to a pod, with the show commands and packet captures from every device it touches: BGP unnumbered underlay, type-2, type-3 and type-5 EVPN routes, symmetric routing proven on the wire, a Palo Alto A/A pair and Cilium.

There is a network inside a GPU server that moves more data than your entire fabric, and you will never configure it. Where NVLink ends is where your job begins: the scale-up versus scale-out boundary, and how GB200 NVL72 moved it.

At a few thousand GPUs, the backend network becomes a probability problem: something is always broken and the hash is always unlucky. The fix is two identical fabrics with zero cross-links. A deep dive into dual-plane design, sized for B300 nodes with 800G per GPU.

Two elephant flows, six trials, six collisions: one uplink carried everything while its twin sat at zero, and every dashboard stayed green. The measured polarization, the four-witness diagnostic chase, and the birthday math production fabrics live with.

Your AI cluster is two networks wearing one badge. One is judged by whether users notice it. The other is judged by whether GPUs wait on it. Frontend vs backend: the traffic, the rules, and how to design the GPU fabric so compute never waits.