# AI DevOps V1 to V2 Upgrade Your team is moving from the original deployment of DuploCloud AI DevOps to something far more powerful. The new V2 version is not just an update — it's a completely new AI DevOps platform that can plan, execute, and manage complex cloud operations autonomously. This guide explains what's new, what changes for your team, and how the upgrade works. *** ## What is AI DevOps V2? AI DevOps V2 is DuploCloud's next-generation AI platform for DevOps teams. It replaces the original AI Studio with a unified system built around a richer model of how AI and engineering teams work together. For a full overview of how the platform is structured, see the [AI DevOps Policy Model](/docs/armor/ai-devops-policy-model.md). At its core, V2 introduces: * [**Workspaces**](/docs/armor/workspaces.md) — dedicated environments where your team and AI agents collaborate, with fine-grained access controls and separation of responsibilities * [**Providers**](/docs/armor/providers.md) — connections to any cloud or tool your team uses (AWS, Azure, GCP, GitHub, Jira, Linear, Slack, and more) * [**Skills and Personas**](/docs/armor/skills.md) — reusable AI capabilities that define how agents behave; combine them into Personas tailored to each team or role * [**Projects**](/docs/armor/projects.md) — a Spec-Driven DevOps process for large, complex work: the agent turns your requirements into a Spec, then a Plan, then executable Tasks * [**Tickets**](/docs/armor/tickets.md) — the familiar conversational interface for quick, focused tasks, now backed by a far more capable agent Everything runs in your own cloud account, fully secure and entirely within your control. *** ## What's New in V2 ![AI DevOps — Create a new ticket](/files/Yeg0H3mNKt0iV0T4ndcT) ### Autonomous AI Agent V1 offered AI assistance for questions and suggestions. V2's agent acts. It reasons through multi-step problems, executes commands, adapts based on results, and works through complex tasks end-to-end — with you in control of every action. ### Projects and Spec-Driven DevOps For large or complex work, V2 introduces [Projects](/docs/armor/projects.md). Describe what you want to accomplish in plain language. The agent turns it into a detailed Spec, creates a phased Plan, and breaks it into Tasks that can be executed in parallel. No more managing large initiatives ticket-by-ticket. ### Skills and Personas [Skills](/docs/armor/skills.md) are the building blocks of what your AI agent knows how to do — Kubernetes troubleshooting, Terraform provisioning, cost optimization, security scanning, and more. Personas group skills by role (SRE, DevOps, Security) so each workspace gets exactly the right capabilities. ### Multi-Cloud and Multi-Tool Providers V1 was limited to your DuploCloud-managed cloud account. V2 connects to any cloud account or tool — multiple AWS accounts, Azure, GCP, GitHub repositories, Jira, Linear, Slack, and custom MCP servers — all with scoped, credential-backed access that your team controls. ### Canvas and Shared Terminal Every ticket opens a Canvas — a live collaborative workspace where you see the agent's reasoning, review suggested commands, and run your own commands in a shared terminal. The agent observes your terminal activity and provides real-time guidance. You stay in control of what gets executed. ### Workspaces Create multiple [workspaces](/docs/armor/workspaces.md) for different teams or functions, each with its own provider access and persona. An L1 SRE workspace might have read-only cloud access; a platform engineering workspace might have full provisioning rights. Access is scoped at the workspace level. To get you started, DuploCloud sets up a default **DevOps workspace** with read-only access to your cloud account and Kubernetes cluster — so your team can explore and query resources from day one. ![AI Admin — Workspaces](/files/UgZadCMqWgvhWhTQPdDt) ### Reports and Artifacts V2 agents can produce reports, generate scripts and configuration files, and save artifacts directly in the ticket's secure workspace — available for review and editing before anything is applied. *** ## What Changes The upgrade is focused on the AI layer. Here's what stays the same and what changes for your team: **What stays the same:** * The **DuploCloud Core Automation Platform** you use today — your tenants, services, infrastructure, and configurations — remains completely unchanged * Any **Add-Ons** you have enabled, such as the Advanced Observability Suite or SIEM, continue to work exactly as before **What changes:** * The current **AI Suite** is replaced by **AI DevOps** — a significantly more capable platform * After the upgrade, your DuploCloud portal will include a **platform switcher** at the top of the interface, letting your team move between the Core Automation Platform and the new AI DevOps platform ![Platform switcher — Switch between Core Platform and AI DevOps](/files/I8248BFgMyFg1YorRaGE) *** ## Upgrade Overview DuploCloud handles the upgrade end-to-end: * **Decommission V1** — remove the legacy AI Studio to make way for V2 * **Update the portal** — add the platform switcher so your team can access both platforms from one login * **Deploy the new AI DevOps platform** — install the new platform alongside your existing DuploCloud environment * **Set up your environment** — configure workspaces, connect your providers, and load the first set of skills and personas so your team is ready to work on day one * Your team gets access to the new platform and our support engineers are available anytime to answer questions, run a walkthrough, or help set up custom workflows *** ## You're in Good Hands The upgrade is designed to be smooth and low-risk, with DuploCloud managing every step. * **Your data stays in your account** — all tickets, configurations, and agent outputs remain in your own cloud environment * **Grows with your team** — after go-live, we can add more providers, build custom skills, or configure additional workspaces as your use cases expand The all new **AI DevOps** is already running in many customer environments. To schedule your upgrade, reach out to your DuploCloud account team. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.duplocloud.com/docs/getting-started/installation/v1-to-v2-upgrade.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.