CAPSTONE · DAY 2
Ship the Acme AI Support Platform
Every module snapped together into one deployable product — end-to-end
Gourav Shah · School of DevOps & AI · Capstone · Day 2
CAP·01
What you'll assemble — the whole platform
One dispatch centre: a native brain, containerized teams, a sealed supply chain.
The container boundary is the rule: the model stays native, everything else is a container.
CAP·02
How the modules connect
Each rung you built maps to exactly one capability of the shipped platform.
Nothing was thrown away — the capstone is the sum of eight modules, wired together.
CAP·03
Move 1 — Serve the model
One brain, two homes: Ollama native on Mac, or vLLM in a container on CPU / GPU.
Swap the engine behind the wall socket — no downstream container changes a single line.
CAP·04
Move 2 — Run the Incident Crew
Four specialists in sequence — MCP tools via ToolHive, Docs Assistant as shared knowledge.
Specialisation with an approval gate — a traceable, auditable incident-response report.
CAP·05
Move 3 — Package as a ModelKit
Weights, system prompt, and quantization config sealed into one OCI artifact.
One command pulls exactly that version — no shared drives, no stray prompt files.
CAP·06
Move 4 — Secure the image
Inventory it, scan it, sign it — and sandbox every tool the agents run.
An image that fails the scan never reaches the registry; a passing one is signed and attested.
CAP·07
Move 5 — Ship via CI
Push to main and the pipeline builds, scans, signs, and publishes on its own.
A passing build produces a signed, attested image any host can pull and verify.
CAP·08
Move 6 — The portability proof
Swap the runtime, re-run platform-check.sh — the output is identical.
The spec, not the vendor, defines the contract — steps 1–7 run unchanged on every runtime.
CAP·09
The arc you shipped
Naive RAG → Agentic RAG → Crew — each pattern earning its keep in turn.
You learned not just how each pattern works, but when it is the right one to reach for.
CAP·10
YOU SHIPPED IT
You can now ship AI on any runtime
Same architecture, new domain — swap the runbooks, keep the wiring.
Build it once. Run it anywhere. · Gourav Shah · School of DevOps & AI
CAP·11