Introduction

Introduction for new users

This introduction explains how to use the platform step by step – from the first project idea to a supervised development run. It is deliberately hands-on and focuses on operation, not on deep architectural decisions.

What is the Software Factory?

The Agentic Software Factory is a local web application that lets you kick off, monitor and trace AI-assisted development processes in a structured way. In version 1 the platform uses Claude Code as the executing agent in the backend.

Instead of driving Claude Code directly from the shell, you work with a UI-centric control plane. This reduces friction and makes runs more transparent.

Mental model

The platform thinks in four layers: Project, Artifacts, Team and Run.

ProjectIdea, target picture and requirements
ArtifactsMarkdown files as the working basis
TeamAgent roles and guardrails
RunConcrete execution with status, logs and validation
Rule of thumb: Good runs start with good artifacts.

Logging in

After starting locally, e.g. via docker compose up, you reach the platform in your browser. You log in with an administrative account that is created at bootstrap via configuration.

SOFTWAREFABRIK_ADMIN_USER=admin
SOFTWAREFABRIK_ADMIN_PASSWORD=ChangeMe-2026!
Important: Without a password set, no bootstrap admin is created on purpose.

Understanding the dashboard

After login you land on the dashboard. It is the command center for projects, runs and status overviews.

Creating a project

Use Create new project to launch a wizard. First you provide required fields such as project title and product name. You then land directly in the editing view.

Adding project content

In the editing screen you maintain the actual project content: target picture, technology preferences, security requirements and free text.

This content flows directly into the generated markdown artifacts.

Generating markdown artifacts

With a click on Generate markdown artifacts, the platform creates the specification files for the agent.

Tip: Review these files carefully. The clearer they are, the more reliable the subsequent run will be.

Agents and teams

The platform models roles such as Architect, Developer, Reviewer, QA, Security Reviewer, Documentation and Merge/Release. In version 1 technically one executing adapter does the work, but roles and teams are already modeled at the domain level.

Creating and starting a run

A run combines project, goal and optionally a team into a concrete execution. Typical fields are project, team, run title and run goal.

A new run starts out in DRAFT. You then move it to READY and start it deliberately.

Monitoring a run

While a run is in progress, you primarily work with three views:

Policies

Policies define in which phases a run may continue automatically and where manual approval is required. By default, non-critical phases are automated, while a deliberate user decision is intended before execution and completion.

Practical tips

Important: You do not need ADRs for this introduction. Focus on wizard, artifacts, run and logs first.