Creating Your First Project

This guide walks you through setting up a new project in Audra Flow, from the initial creation screen all the way to starting your first piece of work. By the end, you will have a fully configured workspace with your team, knowledge base, and first phase ready to go.

Before You Begin

To create a project, you need an Audra Flow account with the Editor role or above. Editors can create and manage their own projects. If you only have Viewer or Guest access, ask your team's administrator to upgrade your role.

If you are brand new to the platform, take a few minutes to read the Welcome to Audra Flow guide first. It covers the key concepts — phases, artifacts, AI agents — that you will encounter throughout this walkthrough.

You will also get more out of the setup process if you have some of these items ready to go:

A brief description of what you are building (even a sentence or two is enough to get started).
Any existing documents you want to upload — product briefs, market research, competitor analyses, technical specs, or brand guidelines.
The email addresses of team members you want to invite.

Step 1: Create from the Dashboard

Sign in to Audra Flow. You will land on the dashboard, which shows all of your existing projects. In the top-right area, click the Create Project button.

You will be asked to fill in the following details:

Project Name — A short, descriptive name for your initiative. This is what your team will see on the dashboard and in navigation, so make it recognisable. For example: “Customer Portal Redesign” or “Inventory Management v2”.
Description — A brief summary of what the project is about. This does not need to be exhaustive; you will flesh out the details during the Discovery phase. A sentence or two that explains the purpose and intended audience is ideal.
Project Type — Choose from Enterprise, SaaS, Startup, or Internal Tool. The project type tailors the default templates and AI agent recommendations to your context. See the Project Types section below for guidance on which to choose.
Target Deadline — The date you are aiming to complete the project. This helps the platform track progress and can be adjusted later if plans change.

Once you have filled everything in, click Create. Audra Flow will set up your workspace and take you straight into it.

Step 2: Understand Your Workspace

After creating the project, you will see the project workspace. Take a moment to get familiar with the layout:

Phase Sidebar — On the left, you will see the five delivery phases listed vertically: Discovery, Definition, Design, Delivery, and Release. Click any phase to see its artifacts. The sidebar also shows a progress indicator for each phase.
Project Overview — At the top of the workspace, you will find the project name, description, type, deadline, and a high-level progress summary. This gives you an at-a-glance sense of where things stand.
Team Members — A section showing everyone who has access to this project, along with their roles. This is also where you invite new people (covered in the next step).
AI Chat — A panel you can open from anywhere inside the project. This is your direct line to the AI agents. You can ask questions, request drafts, or get recommendations tailored to your project.

Good to know: Everything you see in the workspace is scoped to this project. Your knowledge base, artifacts, team members, and AI conversations are all contained here and will not bleed into other projects.

Step 3: Invite Team Members

A project works best when the whole team is on board. To invite people, go to the team members area in your project workspace and click Invite Member.

For each person, enter their email address and choose a role. Here is a quick summary of what each role can do:

Role	What They Can Do
Owner	Full control over the project, including deleting it, managing billing, and changing organisation-level settings. There is typically one Owner per project.
Admin	Manage team membership, configure AI settings, review audit logs, and approve artifacts. Admins handle the day-to-day governance of the project.
Editor	Create, edit, and manage artifacts across all phases. Editors can also use AI agents to generate content and upload documents to the knowledge base. This is the most common role for active contributors.
Viewer	Read-only access to all project content. Viewers can browse artifacts, view the traceability graph, and read AI-generated outputs, but cannot make changes.
Guest	Limited, read-only access to specific artifacts that have been shared with them. Useful for external stakeholders, clients, or cross-team reviewers who only need to see part of the project.

You can always change someone's role later or remove them from the project entirely. Only Owners and Admins can manage team membership.

Step 4: Set Up Your Knowledge Base

The knowledge base is one of the most powerful features in Audra Flow. When you upload documents here, the AI agents can draw on that material to produce recommendations and drafts that are specific to your project — not generic boilerplate.

To add documents, navigate to the Knowledge Base section of your project and click Upload Document. You can upload multiple files at once. Supported formats include PDF, Word documents, plain text, and Markdown.

Here are some examples of documents that work well:

Product briefs or one-pagers — These give the AI agents an overview of the product vision and goals.
Market research and surveys — Helps the UX Researcher agent produce more accurate personas and user journeys.
Competitor analyses — Useful context for goal-setting and differentiation during the Discovery phase.
Technical specifications or architecture docs — Gives the Architect agent a head start on understanding your existing systems and constraints.
Brand guidelines or style guides — Helps keep AI-generated content consistent with your organisation's tone and terminology.

Tip: You do not need to have everything ready before you start. You can upload documents at any point during the project, and AI agents will incorporate the new material automatically.

Step 5: Begin Discovery

With your project created, team invited, and knowledge base seeded, you are ready to start working. Click on Discovery in the phase sidebar to open the first phase.

The Discovery phase is where you lay the groundwork. Here is what you can do:

Capture Goals — Define the strategic objectives for your project. What are you trying to achieve? Who benefits? What does success look like? Each goal becomes an artifact that other work can trace back to.
Conduct Stakeholder Research — Record insights from conversations with stakeholders, customers, and subject matter experts. The UX Researcher agent can help you structure interview notes into actionable findings.
Run Competitor Analysis — Document what competitors are doing, where the gaps are, and how your product will differentiate. If you uploaded competitor research to your knowledge base, the AI agents can help synthesise it.

As you create artifacts in Discovery, they become the foundation for everything that follows. Personas in the Definition phase will reference your goals. User stories in the Delivery phase will trace back to those personas. This chain of connections is what makes Audra Flow's traceability so valuable.

Project Types

When you create a project, you choose one of four types. Each type adjusts the default templates, AI agent prompts, and recommended workflows to fit your context. Here is how to decide:

Project Type	Best For	What Changes
Enterprise	Large-scale products for established organisations with complex stakeholder landscapes, compliance requirements, and multi-team coordination.	Templates emphasise governance, approval workflows, and detailed traceability. AI agents factor in enterprise concerns like security, scalability, and regulatory compliance.
SaaS	Cloud-based software products with subscription models, user onboarding flows, and iterative release cycles.	Templates focus on user acquisition, retention metrics, and multi-tenant architecture. AI agents prioritise user experience, onboarding journeys, and pricing considerations.
Startup	Early-stage products where speed matters, scope is still being defined, and the team is lean.	Templates are streamlined for rapid iteration. AI agents focus on MVP scoping, market validation, and lean-experiment design. Less emphasis on heavy governance.
Internal Tool	Tools built for use within your own organisation — operations dashboards, workflow automation, internal portals.	Templates focus on employee workflows, integration with existing internal systems, and adoption strategies. AI agents consider change management and internal stakeholder alignment.

Not sure which to pick? Start with the one that most closely matches your situation. You can update the project type later from the project settings if your needs change.

Tips for Success

Here are some practical suggestions that teams find helpful when getting started with Audra Flow:

Seed the knowledge base early. The more context the AI agents have, the better their suggestions will be. Even rough drafts, meeting notes, or old slide decks can provide valuable input. You do not need polished documents.
Start with goals, not solutions. The Discovery phase exists for a reason. Resist the urge to jump straight to user stories. Teams that invest time in clear goals and solid research produce better artifacts downstream and spend less time reworking things later.
Check the Product Guru early and often. The Product Guru agent analyses your project holistically — across all phases and artifacts — and highlights gaps, inconsistencies, or opportunities you might have missed. Think of it as a second set of eyes on your entire project.
Use templates when available. Each project type comes with pre-configured templates for common artifact types. Templates give you a solid starting point and ensure consistency across your team. You can always customise them after creation.
Invite stakeholders as Viewers or Guests. You do not need to give everyone edit access. Adding stakeholders with read-only roles keeps them informed and makes it easy to gather feedback without risking accidental changes to your work.
Let traceability work for you. As you create artifacts, link them to the work that informed them. When a user story connects to a persona, which connects to a goal, which connects to research — you have a complete chain of reasoning that makes reviews, audits, and handoffs far smoother.
Review AI-generated content before finalising. AI agents are powerful drafting partners, but they work best when a human reviews and refines their output. Treat AI suggestions as a strong first draft, not a finished product.

Next Steps

Your project is set up and ready to go. Here is where to head next depending on what you need:

Discovery Phase Guide — Dive deeper into capturing goals, conducting research, and building your evidence base.
Working with AI Agents — Learn how to get the best results from the UX Researcher, Product Owner, Architect, and Product Guru.
Knowledge Base & Documents — Advanced tips for organising your document library and maximising AI context.
Roles & Permissions — Full details on what each role can and cannot do across the platform.
Collaboration & Approvals — Set up approval gates, manage comments, and use the audit trail for governance.

Need help? Open the AI chat inside your project and ask the Product Guru for suggestions. It can review your current setup and recommend what to work on next based on what you have so far.