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

# About CloudThinker

> See how the ideas in this field guide map to CloudThinker features, and start a recommendation-only pilot on your own environment.

*CloudThinker builds Frontier Investigation Agents: agents that investigate problems across your cloud and propose fixes. Writes run only under your approval policy.*

This page maps each practice in the field guide to a product page, so you can check every claim before you run a pilot.

## What CloudThinker is

Every workspace has one built-in assistant, also called **CloudThinker**. It splits large tasks across temporary subagents that work in parallel, and your team can add [custom agents](https://docs.cloudthinker.io/guide/agents/customize.md) for its own systems. The [agents overview](https://docs.cloudthinker.io/guide/agents/overview.md) explains how they fit together.

Agents work through [connections](https://docs.cloudthinker.io/guide/connections/overview.md), the saved credentials CloudThinker uses to reach a system: AWS, Azure, Google Cloud, local clouds such as [GreenNode](https://docs.cloudthinker.io/guide/connections/greennode.md) and [FPT Cloud](https://docs.cloudthinker.io/guide/connections/fptcloud.md), Kubernetes, databases, observability tools, and more. On-premise systems are reachable through [VMware](https://docs.cloudthinker.io/guide/connections/vmware.md), [OpenStack](https://docs.cloudthinker.io/guide/connections/openstack.md), [SSH](https://docs.cloudthinker.io/guide/connections/ssh.md), or an [Environment](https://docs.cloudthinker.io/guide/workers.md), a folder on your own machine where CloudThinker reads files and runs commands over an outbound connection.

Each request runs through one loop: detect the problem, analyze the root cause, resolve it under your approval policy, and validate that the fix held ([full explanation](https://docs.cloudthinker.io/index.md)).

## The products

| Product | What it does | Start here |
| :- | :- | :- |
| **Resolve** | Investigates incidents, finds the root cause, and proposes a fix that runs once approved | [Resolve overview](https://docs.cloudthinker.io/guide/incident/overview.md) |
| **Review** | Reviews every pull or merge request and posts findings as comments | [Review overview](https://docs.cloudthinker.io/guide/code-review/overview.md) |
| **Cyber** | Tests your running web apps and APIs and proves each finding with evidence | [Cyber overview](https://docs.cloudthinker.io/guide/security/cyber-overview.md) |
| **Optimize** | Finds cloud cost waste and recommends savings | [Optimize overview](https://docs.cloudthinker.io/guide/cost-optimization/overview.md) |
| **Customize** | Shapes how agents work in your workspace: custom agents, skills, knowledge, credentials, and approvals | [Customize](https://docs.cloudthinker.io/guide/agents/customize.md) |
| **Automation** | Runs agent instructions on a schedule, a webhook call, a repository event, or a probe | [Automations](https://docs.cloudthinker.io/guide/automation/automations.md) |

All of them share the same connections, approval policy, and audit trail.

## Where the field guide's controls live

| Practice in this guide | CloudThinker feature |
| :- | :- |
| Autonomy earned one step at a time ([Chapter 7](https://docs.cloudthinker.io/learn/aio/chapter-7-humans-on-the-loop.md)) | [Approval mode](https://docs.cloudthinker.io/guide/approvals/approval-mode.md): **Manual** (a person approves every write) or **Auto** (Rules first, optional AI judgment, then ask a person or refuse) |
| Action policy per operation ([Chapter 6](https://docs.cloudthinker.io/learn/aio/chapter-6-trust-governance.md)) | [Approval Rules](https://docs.cloudthinker.io/guide/approvals/rules.md) that allow, ask first, or deny specific writes |
| Humans on the loop ([Chapter 7](https://docs.cloudthinker.io/learn/aio/chapter-7-humans-on-the-loop.md)) | [Approvers](https://docs.cloudthinker.io/guide/approvals/approvers.md), the people who review actions waiting for approval |
| Sensitive data kept from models ([§6.3](https://docs.cloudthinker.io/learn/aio/chapter-6-trust-governance.md)) | [Guardrails](https://docs.cloudthinker.io/guide/security/custom-guardrails.md) show agents a placeholder instead of emails, card numbers, API keys, and your own ID patterns |
| Model calls on your own account | [BYOK](https://docs.cloudthinker.io/guide/byok.md) (bring your own LLM credentials) |
| Evidence for change management | [Audit Logs](https://docs.cloudthinker.io/guide/security/audit-logs.md) under **Admin Settings → Audit Logs** |
| Data residency | [Deployment options](https://docs.cloudthinker.io/guide/deployment/overview.md): CloudThinker Cloud, and Cloud plus [Environments](https://docs.cloudthinker.io/guide/workers.md) (beta) for work that must run on your machines. Dedicated, self-hosted, and air-gapped deployments are early access, through a design-partner program. The hosting region isn't published, so ask for it. |
| The memory layer ([Chapter 9](https://docs.cloudthinker.io/learn/aio/chapter-9-roadmap.md)) | [Memory](https://docs.cloudthinker.io/guide/memory.md) and [Knowledge](https://docs.cloudthinker.io/guide/knowledge.md) |

## Run the 90-day pilot

[Chapter 9](https://docs.cloudthinker.io/learn/aio/chapter-9-roadmap.md) recommends starting recommendation-only and earning autonomy on evidence. In CloudThinker, week one takes three moves.

> [!NOTE]
>
> **Prerequisite:** changing the Approval mode needs the workspace Admin role. Other roles see the picker as view only.

**1. Switch the workspace to Manual**

New workspaces start on **Auto · Rules + AI · Ask me**, so change it before you connect anything. Open **Approvals** in the sidebar, then the **Approval mode** tab. Under **Workspace mode**, select **Manual**.

If you plan to run [Automations](https://docs.cloudthinker.io/guide/automation/automations.md), also go to **Run types**, click **Override** on the **Automations** row, and select **Manual**. That row defaults to **Auto · Rules + AI · Refuse** and doesn't follow the workspace mode.

**Success state:** the picker shows **Manual**, and every write waits for a person. Reads still run.

**2. Connect one bounded, low-risk system with read-only access**

Pick something you can afford to experiment on, such as a staging Kubernetes cluster or one non-production AWS account. Use a read-only IAM role or service account, as in the [AWS](https://docs.cloudthinker.io/guide/connections/aws.md#required-permissions), [Azure](https://docs.cloudthinker.io/guide/connections/azure.md), or [Google Cloud](https://docs.cloudthinker.io/guide/connections/gcp.md) setup. Follow the [quickstart](https://docs.cloudthinker.io/quickstart.md) to add it under connections.

**Success state:** the connection shows a **Connected** status.

**3. Record a baseline, then compare monthly**

Export the last 90 days of mean time to resolve (MTTR) and pages per week from your paging and ticket tools, and note your monthly cloud cost. CloudThinker can't measure the time before you connected it. [Resolve Insights](https://docs.cloudthinker.io/guide/incident/insights.md) starts tracking once Resolve receives incidents from your alert source. [Chapter 8](https://docs.cloudthinker.io/learn/aio/chapter-8-measuring.md) covers which metrics to pick.

**Success state:** you have a dated baseline to compare against **Resolve → Insights** at day 30, 60, and 90.

For the later phases (Approvers, Allow Rules, and switching to **Auto**), follow [§9.6](https://docs.cloudthinker.io/learn/aio/chapter-9-roadmap.md). Allow Rules decide only once CloudThinker turns on [Rule enforcement](https://docs.cloudthinker.io/guide/approvals/rules.md#troubleshooting) for your workspace; until then the Approval mode alone decides, so **Manual** is the control that holds every write today.

Bring the eight data-control questions from [§6.3](https://docs.cloudthinker.io/learn/aio/chapter-6-trust-governance.md) to your evaluation. For private deployment or procurement questions, [contact the team](https://cloudthinker.io/contact).

## Next steps

> [card] [Quickstart](https://docs.cloudthinker.io/quickstart.md)
>
> Connect a cloud account and run your first investigation.

> [card] [Approvals](https://docs.cloudthinker.io/guide/approvals/overview.md)
>
> Set the approval policy before agents make any change.


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