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

What you'll assemble — the whole platform

One dispatch centre: a native brain, containerized teams, a sealed supply chain.

How the modules connect

Each rung you built maps to exactly one capability of the shipped platform.

Move 1 — Serve the model

One brain, two homes: Ollama native on Mac, or vLLM in a container on CPU / GPU.

Move 2 — Run the Incident Crew

Four specialists in sequence, sharing one model and two shared services.

Move 3 — Package as a ModelKit

Weights, system prompt, and quantization config sealed into one OCI artifact.

Move 4 — Secure the image

Inventory it, scan it, sign it — and sandbox every tool the agents run.

Move 5 — Ship via CI

Push to main and the pipeline builds, scans, signs, and publishes on its own.

Move 6 — The portability proof

Swap the runtime, re-run platform-check.sh — the output is identical.

The arc you shipped

Naive RAG → Agentic RAG → Crew — each pattern earning its keep in turn.

YOU SHIPPED IT

You can now ship AI on any runtime

Same architecture, new domain — swap the runbooks, keep the wiring.

Now open Capstone · Lab.  ·  Gourav Shah · School of DevOps & AI