Axiom StudioAXIOMSTUDIO
All docs

Getting Started with VibeFlow

This guide walks you through setting up your first VibeFlow project and connecting an AI agent to start building.

Prerequisites

  • An Axiom Studio account (sign up at axiomstudio.ai)
  • A git repository for your project
  • An AI coding agent (Claude Code CLI, Cursor, Gemini, or similar)

Step 1: Configure Object Storage

Before using VibeFlow, configure where your documents and assets are stored:

  1. Navigate to Storage in the sidebar
  2. Select your storage provider (S3, MinIO, Cloudflare R2, or Google Cloud Storage)
  3. Enter your endpoint URL, bucket name, region, and credentials
  4. Click Test Connection to verify
  5. Save your configuration

Step 2: Create Your First Project

  1. Go to VibeFlow in the sidebar
  2. Click + New Project
  3. Enter a project name (e.g., "my-app") and optional description
  4. Set the default git branch (usually main)
  5. Click Create

Your project is now in in_review status, ready for planning.

Step 3: Add Features and Work Items

Create a Feature

Features are major areas of work within a project:

  1. Open your project
  2. Click + New Feature
  3. Enter a name (e.g., "User Authentication"), description, and priority
  4. The feature starts in in_review status

Create Todos

Todos are specific tasks within a feature:

  1. Open a feature
  2. Click + New Todo
  3. Enter a title (e.g., "Add login form with email/password"), description, and priority
  4. Set the target git branch
  5. Click Create

Create Issues

Issues are standalone bugs or tasks at the project level:

  1. From the project view, click + New Issue
  2. Enter title, description, and priority
  3. Optionally link to a feature
  4. Click Create

Step 4: Prepare Work Items

Move work items through the planning stages:

  1. in_review → Review the item with stakeholders
  2. planning → Plan the implementation approach
  3. ready_to_implement → Mark as ready for an agent to pick up

Items in ready_to_implement status will be picked up by connected agent sessions.

Step 5: Connect an AI Agent

Using Claude Code CLI

  1. Go to your project's Setup tab
  2. Copy the MCP server configuration for Claude CLI
  3. Add the configuration to your Claude Code settings
  4. Start a new Claude Code session with the VibeFlow persona prompt

Using Other Agents

VibeFlow supports multiple agent types:

  • Claude Desktop — Copy the MCP config to your Claude Desktop settings
  • Cursor — Add the MCP server URL to your Cursor configuration
  • Gemini — Configure via the Gemini MCP integration
  • OpenAI Codex — Connect via the MCP bridge

Each agent type has specific setup instructions in the Setup tab.

Step 6: Watch Agents Work

Once connected, agents autonomously:

  1. Poll for ready work items on your branch
  2. Claim the highest-priority item
  3. Plan the implementation (read docs, analyze code)
  4. Implement the code changes
  5. Test the implementation
  6. Commit to git with traceability
  7. Mark done and move to the next item

You can watch real-time progress in the Session Chat — agents publish execution logs and ask you questions when they need input.

Step 7: Review and Verify

After agents complete work:

  1. Security Review — The security lead persona reviews for vulnerabilities
  2. QA Verification — The QA lead persona tests functionality
  3. Both reviews must pass before a work item is fully complete

Next Steps

  • Projects — Learn about project management in detail
  • Personas — Set up a multi-persona agent team
  • Agent Sessions — Deep dive into autonomous agent workflows