# How to manage large complex projects

This walkthrough demonstrates how DuploCloud's AI DevOps suite takes an existing e-commerce order service running on AWS EKS from zero observability and security hardening to a fully production-ready, SOC 2-compliant platform — in a single automated workflow.

***

## The Starting Point

A simple order service is deployed in a sandbox environment. The goal: scale the platform and pass a SOC 2 audit in 90 days. The microservice architecture runs 5–10 services on AWS EKS with no observability, no cost controls, no automated pipelines, and no security hardening.

![Demo overview](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-3cecd40b847a979c917e980501c6e2d640964867%2Fdemo-01-overview.png?alt=media)

***

## Step 1 — Connect the Service to DuploCloud

Before any work can begin, the service must be connected to DuploCloud. Providers and scopes for both AWS and Kubernetes have already been created.

**Verify AWS Connection** — An AWS provider is configured with the correct credentials and scope. Confirming the sandbox nodes are running verifies DuploCloud is connected to the AWS account.

![AWS sandbox nodes running](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-f9d4b36d1678bbe0bb3c783b29e79a928849802d%2Fdemo-03-aws-nodes-running.png?alt=media)

**Verify Kubernetes Connection** — A Kubernetes provider is configured with credentials and a scope defining what DuploCloud can access. Confirming the pods from the order service are visible verifies the connection.

![Pods running](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-ff487a2d31f2cae4cd183c59ff38613e0f11d14a%2Fdemo-05-pods-running.png?alt=media)

***

## Step 2 — Set Up the Workspace

All work inside DuploCloud happens inside **workspaces**. Select the workspace for this project — it already has the required skills and agents configured.

![Workspaces](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-9cb24feae0dbaf4c60d3c62e91b7f8b0d03bd0c5%2Fdemo-06-workspaces.png?alt=media)

Scroll down to **Cloud Providers** and add the new scope for the service. Then under **Kubernetes**, add the scope that gives the system access to this particular service. Hit **Update** to save.

![Adding scopes to workspace](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-6db856bf712522a594aa20f990857f15f9a68b8a%2Fdemo-07-adding-scopes-to-workspace.png?alt=media)

![Update workspace](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-ff41b18c292d8c6243ca79ed7e0f518cfaac0bbb%2Fdemo-08-update-workspace.png?alt=media)

***

## Step 3 — Create a Project

Navigate to **AI DevOps → Projects**. Create a new project, give it a name, and select the right scopes and skills. DuploCloud uses a **spec-driven approach** (as recommended by Anthropic) — open the **AI Planner** and provide a prompt with all project requirements.

![Create new project](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-58802bfe87b43e5c146afc3bd06ecf51af29ad37%2Fdemo-09-create-project.png?alt=media)

![AI Planner with requirements prompt](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-7b7782a6fc56c261ff805fb59af00cca73426fcd%2Fdemo-10-ai-planner-prompt.png?alt=media)

DuploCloud runs a **discovery process**, asking for user input where required.

![Discovery process running](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-2bb3056f4775037907c615318f0ec88349a0336e%2Fdemo-11-discovery-process.png?alt=media)

Once complete, it produces a **spec document** with high-level requirements, then a **plan document** with the step-by-step process divided into phases and tasks, and finally a list of **execution tasks** divided into stages.

![Spec document](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-4e3d899a5f9d541fbbb04227400b83c3848d55e8%2Fdemo-12-spec-document.png?alt=media)

![Plan document](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-4432d73108a965e985427ff70a9b53b20de10540%2Fdemo-13-plan-document.png?alt=media)

![Execution tasks by stage](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-56a321c7e2ebe2bd73dcfdfb349aa9154a125060%2Fdemo-14-execution-tasks.png?alt=media)

> **Tip:** Save the spec, plan, and execution task files — Claude Code can use them as context when picking up tasks directly in your IDE.

***

## Step 4 — Project Dashboard and Tickets

Back on the project dashboard, the agent has created **individual tickets** for each task, grouped by phase.

![Project dashboard with tickets](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-15851e86b958986d505b65af7434b0fe899b4998%2Fdemo-15-project-dashboard-tickets.png?alt=media)

![Phases with tickets](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-bce39208cf28fe9c6a44893b6cd0a840651001a9%2Fdemo-16-phases-with-tickets.png?alt=media)

***

## Step 5 — Execute the First Task

Open the first ticket to find the current state — the metrics server is not installed and no metrics are reporting. DuploCloud works autonomously, installs the metrics server, and metrics are now being reported.

![First task ticket open](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-e9a34f5ab52873eefcbbe6e71d45f55abccb4691%2Fdemo-17-first-task-ticket.png?alt=media)

![Metrics server missing](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-1bac7b85c47465eae4f614c857d1c7103834223f%2Fdemo-18-metrics-server-missing.png?alt=media)

![Metrics now reporting](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-a02207ca609ab0f2691fb892de0d1cd6a895b163%2Fdemo-19-metrics-reporting.png?alt=media)

***

## Step 6 — Collaborate via Claude Code

The next task is assigned to a team member (John) who prefers working from his IDE using DuploCloud's **Claude Code plugin**. He initializes the workspace and project and picks up right where the team left off.

![John using Claude Code plugin in IDE](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-39b4b4f83f4376cdfceb11c269689c9e73e09191%2Fdemo-21-ide-claude-code-plugin.png?alt=media)

John executes two tickets via Terraform — enabling EKS control plane logging to CloudWatch, then enabling Container Insights to collect pod-level metrics via a CloudWatch agent daemon set.

![Container Insights Terraform change](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-a0e652df535bcae72a37edacb46d0a35cd75217d%2Fdemo-22-container-insights-terraform.png?alt=media)

Everything done in Claude Code is automatically mirrored back in the ticket.

![Changes mirrored in ticket](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-717614aef5c132d5337cd8676530c699a946c5b1%2Fdemo-23-changes-mirrored-in-ticket.png?alt=media)

***

## One Task at a Time, End to End

DuploCloud doesn't hand you a list of recommendations — it works through them. Each phase of the plan is broken into discrete tickets, and the agent executes them one by one: running commands, validating results, and moving to the next. Whether a task is handled autonomously or picked up by a team member via Claude Code, every action is logged and every outcome is verified before the project moves forward.

![Tickets executed one by one](https://2471407984-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F68cb0s9ce5UIUKWPuYs8%2Fuploads%2Fgit-blob-fb7b8e9978ebe628c6c76fc1c055ec34ab51f892%2Fdemo-tackle-tasks.png?alt=media)