> ## Documentation Index
> Fetch the complete documentation index at: https://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, running Altrum, or auditing.

Pick the path closest to your job and read in order. The role named with each path is the one that usually fits; your role decides what you can change, never what you can read here. See [Members and roles](/members-and-roles.md).

## Governance, risk and compliance

You keep the register of AI systems, run assessments and decide which controls apply. Usually a **Governance Lead**.

1. [How Altrum works](/how-altrum-works.md), then [Home](/home.md).
2. [Discover](/discover.md) the AI already in use, and register it as [AI systems](/ai-systems.md) with a [risk rating](/ai-systems/risk-rating.md).
3. Decide which [models](/model-catalog.md) and [MCP servers](/mcp-servers.md) your organization may use.
4. Run [assessments](/assessments/overview.md) and read their [results](/assessments/results.md).
5. Turn the results into live controls with [guardrail suggestions](/guardrails/suggestions.md) and [Configure guardrails](/guardrails/configure.md).
6. Approve AI systems before they go live: [Lifecycle](/ai-systems/lifecycle.md).
7. Follow [Reporting](/reports.md), [Alerts](/alerts.md) and [Incidents](/incidents.md).
8. Hand an auditor a [compliance report](/compliance.md).

## Security

You decide what an AI system may receive and say, and you need proof that it is enforced. Usually a **Governance Lead**, or an **Admin** if you also run the AI Gateway.

1. [Guardrails](/guardrails/overview.md) and [Guardrail types](/guardrails/types.md).
2. [Test guardrails](/guardrails/test.md), [Versions](/guardrails/versions.md) and [Red-team runs](/guardrails/red-team.md).
3. [Guardrails at runtime](/guardrails/at-runtime.md): how every request is checked, and why a failed check stops it.
4. [Organization guardrails](/guardrails/organization.md) for traffic that belongs to no AI system.
5. [Request logs](/ai-gateway/request-logs.md) and [Security and data](/security-and-data.md): what Altrum keeps, and where.

## AI builders

You build applications and use coding agents, and you want them governed without rewriting them. Usually a **Member** who owns the AI systems they build.

1. [AI Gateway overview](/ai-gateway/overview.md), then [Send your first request](/ai-gateway/quickstart.md).
2. [SDKs](/ai-gateway/sdks.md) and [Coding agents](/ai-gateway/coding-agents.md).
3. [MCP tools](/ai-gateway/mcp.md) and [Prompts](/ai-gateway/prompts.md).
4. [Handle errors](/ai-gateway/handle-errors.md), so your application knows what to do when a guardrail or a budget stops a request.
5. The [API reference](/api-reference/introduction.md) for every endpoint and header.

## Administrators

You run your organization in Altrum: people, access and the AI Gateway's settings. Usually an **Admin** or an **Owner**.

1. [Sign in](/sign-in.md), [Members and roles](/members-and-roles.md) and [Plans and modules](/plans-and-modules.md).
2. [Provider credentials](/ai-gateway/provider-credentials.md) and [Virtual keys](/ai-gateway/virtual-keys.md).
3. [Budgets and rate limits](/ai-gateway/budgets-and-limits.md), [content logging](/ai-gateway/request-logs.md), the [semantic cache](/ai-gateway/semantic-cache.md) and [OpenTelemetry](/ai-gateway/opentelemetry.md).
4. [Alerts](/alerts.md): which rules run and who hears about them.
5. [Access reviews](/access-reviews.md) each quarter.

## Auditors

You check that the controls exist and work, and you change nothing. Usually an **Auditor**. The role lasts until an owner or admin removes it or gives you another one.

1. [Home](/home.md) and [Posture](/ai-systems/posture.md).
2. [Compliance reports](/compliance.md) for one AI system or the whole organization.
3. The [Audit trail](/audit-trail.md): who changed what, and when.
4. [Access reviews](/access-reviews.md), the [Model catalog](/model-catalog.md) and [MCP servers](/mcp-servers.md): what was kept, approved or blocked, by whom and why.
5. [AI systems](/ai-systems.md) and [Incidents](/incidents.md): ratings, approvals, history, and how problems were handled.


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