> ## Documentation Index
> Fetch the complete documentation index at: https://dev-docs.altrum.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Go from your invitation to live guardrails on your first AI system.

This walk-through takes an owner or admin from the invitation email to an AI system with live guardrails. Allow about half an hour, most of it for the assessment conversation.

<Steps>
  <Step title="Accept your invitation">
    Open the link in the email **You are invited to join your organization on Altrum**. Enter your first name, last name and a password of at least 12 characters, or choose **Continue with Google** with the Google account for the invited address. Select **Create account**. You land on **Home**. The link works once and for 7 days.
  </Step>

  <Step title="Add an AI system">
    Open **AI systems** and choose **Add AI system**. Give it a name, a description and its purpose, choose its owner and initial risk, and pick the model providers it uses. Saving takes a few seconds. The new AI system is inactive until you activate it.
  </Step>

  <Step title="Start the assessment">
    On the AI system's page, choose **Start assessment**, then **Start the assessment**. The assistant asks about your AI system one question at a time. Answer in your own words, and attach documents that describe it if you have them. **Save and exit** keeps your answers for later.
  </Step>

  <Step title="Submit your answers">
    When the assistant has what it needs, it asks whether you are ready. Choose **Yes, submit my answers**. The page shows its progress: saving your answers, sending them for assessment, finding your risks and controls.
  </Step>

  <Step title="Review the results">
    The results show the risks, the controls and the guardrails in scope. On the **Guardrails** tab, each guardrail is marked **Configured** or **Needs your action**.
  </Step>

  <Step title="Configure the guardrails">
    Choose **Configure guardrails**. When the banner says your assessment suggests settings, choose **View suggestions**, then **Add them to my draft**. Set up any guardrail still marked **Needs your setup**, or switch it off. Choose **Save draft**.
  </Step>

  <Step title="Test the draft">
    Choose **Test guardrails**, type a message that should be caught, and choose whether to treat it as something a person sends or something the model answers. The result says whether it was blocked, masked or logged, and which guardrail fired.
  </Step>

  <Step title="Complete the assessment">
    Choose **Complete Assessment** and confirm. Your saved draft becomes the live version and the assessment closes. The AI system's **Guardrails** tab now shows **Live: version 1**.
  </Step>

  <Step title="Activate the AI system">
    Back on the AI system's page, choose **Activate** and confirm. The owners of your organization and the AI system's owner are emailed.
  </Step>
</Steps>

## Next

* Invite the people who should see or change this work: [Members and roles](/members-and-roles).
* Learn what each guardrail checks: [Guardrail types](/guardrails/types).
* Prepare for the AI Gateway, which applies the live guardrails to your application's traffic: [AI Gateway](/ai-gateway/overview).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.