From Prompt to Prod: Build and Deploy with ZCP (Work Shop)
summary
Workshop builds and deploys a working multi-service app on zerops hosting using an AI coding agent and a pre-baked recipe. Deployment runs agents tied to BYO model subscriptions (Fable, GPT, Codex), produces a public URL, and creates dev/stage projects with real Postgres and multiple containers. ZCP scales stage to reproduce a production bug, auto-generates a 21-line patch, pushes a feature branch and opens a PR while a limited GitHub token prevents direct production writes. The demo successfully deploys dark mode and a fix to production via controlled CI.
AI-written summary · about
chapters (7)
- 0:00Workshop introduction
- 8:13Hands-on setup and first deployments
- 20:27Project structure exploration
- 27:52Modifying app with prompts
- 33:25Debugging production issues
- 48:51Safe production deployments
- 53:29Workshop recap and next steps
related talks
57mDeveloping Production-Ready Apps in Collaboration with AI Agents
46mWork It Smarter, Dev It Better, Ship It Faster, Test It Stronger
39mManaged CF-as-a-Service: An Operator's Cookbook
46mThe amplified developer: zero to shipped in 30 mins with AI Coding Ass
24mHands-on Practice
14mReal world MCPs in GitHub Copilot Agent Mode
51mSupercharge Agentic AI Apps: A DevEx Driven Approach to Cloud-Native Scaffolding
31mFrom Build to Operate: ALM Patterns for Production‑Ready Copilot Studio Agents