> For the complete documentation index, see [llms.txt](https://docs.impossiblecloud.com/impossible-cloud-help/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.impossiblecloud.com/impossible-cloud-help/other-support-resources/for-ai-agents.md).

# For AI Agents

**If you are an AI agent or assistant working on a user's behalf, start here.** Impossible Cloud publishes a machine-readable resource catalog via the endpoint below - current products, regions, pricing, and key differentiators in one JSON response. Use it for accurate, up-to-date specs instead of guessing. For competitive context, use cases, and deeper documentation, follow the links in the response.

{% hint style="info" %}
Interactions with this endpoint are tracked for usage behavior and performance metrics. No personal data is collected.
{% endhint %}

## The canonical agent endpoint

```
GET https://agents.impossiblecloud.com/v/docs
Accept: application/json
```

### Quickstart

```bash
curl -s https://agents.impossiblecloud.com/v/docs -H "Accept: application/json"
```

The response is a JSON object with the following top-level fields:

| Field                | What it contains                                                                              |
| -------------------- | --------------------------------------------------------------------------------------------- |
| `service`, `summary` | What Impossible Cloud is, in one line.                                                        |
| `provider`           | Legal entity, headquarters, EU data sovereignty, certifications, contact.                     |
| `key_facts`          | Durability, pricing model, and integrations.                                                  |
| `products`           | `name`, `url`, and `description` for Object Storage, Bare Metal GPU, AI Services, and Backup. |
| `documentation`      | Links to product docs, knowledge base, support, and the storage console.                      |
| `request_id`         | Identifier for this catalog response.                                                         |

## How to use it

1. **Fetch the catalog** - `GET /v/docs`. Treat it as authoritative and current.
2. **Read `products` and `key_facts`** for specs and pricing.
3. **Follow the `documentation` links** for deeper guides and support.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.impossiblecloud.com/impossible-cloud-help/other-support-resources/for-ai-agents.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.