> ## 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.

# Start by role

> Find the pages that matter for your job: governance and risk, security, building with AI, or running your organization in Altrum.

Each path below is a reading order. Your role in Altrum (Owner, Admin or Member) decides what you can change, not which pages you read.

## Governance, risk and compliance

You keep the register of AI systems, run the assessments and decide which controls apply.

1. [How Altrum works](/how-altrum-works): the pieces and how they connect.
2. [AI systems](/ai-systems): register what your organization uses, with an owner and an initial risk rating.
3. [Assessments](/assessments/overview): the interview, submitting it, and what happens next.
4. [Assessment results](/assessments/results): risks with NIST AI RMF and ISO/IEC 42001 references, controls, and the guardrails in scope.
5. [Guardrail suggestions](/guardrails/suggestions) and [Configure guardrails](/guardrails/configure): turn the scope into live guardrails.
6. [Reports](/reports): coming soon.

## Security

You decide what an AI system may receive and say, and you need to know it is enforced.

1. [Guardrails](/guardrails/overview): what a guardrail checks, and Log only, Block and Mask.
2. [Guardrail types](/guardrails/types): data protection, custom patterns, harmful content, prompt injections and the rest.
3. [Test guardrails](/guardrails/test) and [Versions](/guardrails/versions): check a draft, and see what is live.
4. [Guardrails at runtime](/guardrails/at-runtime): how requests are checked and why a failed check stops the request. Coming soon.
5. [Security and data](/security-and-data): where your data lives and what Altrum keeps.
6. [Provider credentials](/ai-gateway/provider-credentials) and [Request logs](/ai-gateway/request-logs): coming soon.

## AI builders

You build the applications and use coding agents, and you want them governed without rewriting them.

1. [AI Gateway](/ai-gateway/overview): what changes for your application. Coming soon.
2. [Gateway quickstart](/ai-gateway/quickstart): your first request through Altrum.
3. [Endpoints](/ai-gateway/endpoints) and [SDKs](/ai-gateway/sdks): OpenAI, Anthropic and Google request formats.
4. [Coding agents](/ai-gateway/coding-agents): Claude Code, Codex CLI, Gemini CLI, Cursor and Claude Desktop.
5. [MCP tools](/ai-gateway/mcp): use your organization's MCP servers through Altrum.
6. [Guardrail types](/guardrails/types): what can stop a request, so your application handles it.

## Administrators

You run your organization in Altrum: people, access and the AI Gateway's settings.

1. [Sign in](/sign-in): invitations, passwords and sessions.
2. [Members and roles](/members-and-roles): invite, change roles, disable and remove.
3. [Account and organization](/account-and-organization): your details and the organization profile.
4. [Budgets and rate limits](/ai-gateway/budgets-and-limits) and [Virtual keys](/ai-gateway/virtual-keys): coming soon.
5. [Support](/support): raise a ticket.


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