> For the complete documentation index, see [llms.txt](https://docs.contextual.io/documentation-and-resources/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.contextual.io/documentation-and-resources/components-and-data/agents/types-of-agents/http-to-flow.md).

# HTTP to Flow

**HTTP to Flow** agents utilize HTTP-In nodes to receive and respond to HTTP requests, enabling them to serve as efficient interfaces for web-based communications. This type of agent is particularly effective for creating dynamic endpoints that interact with users or external systems via the web.

**Key Features:**

* **HTTP Interfaces**: Capable of handling direct HTTP requests, these agents facilitate the development of RESTful APIs, webhooks, and other web services.
* **Customizable Workflows**: Developers have the flexibility to create complex processing sequences that start from an HTTP request, allowing for intricate interactions within web applications.
* **Use Cases**: These agents are best suited for building web APIs, managing user interactions through web forms, or providing gateway services that connect different web-based applications and services.

## Keep the Agent Available During Maintenance

Contextual regularly maintains the infrastructure that runs Agents, for example to apply upgrades or replace servers. During maintenance, an Agent's instances can stop and start again on another server.

* **Minimum of 2 or more parallel instances:** Contextual keeps at least half of the Agent's instances running, so the Agent keeps serving requests.
* **Minimum of 1:** the Agent's only instance can stop. Requests fail until it starts again.

This applies only to infrastructure maintenance. Updating the Agent to a new Flow version is separate. Those updates already roll out without downtime, whatever the minimum.

To keep an HTTP to Flow Agent available for clients and users who depend on it:

1. Choose **Components > Agents**, then choose the Agent.
2. On the **Definition** tab, under **Parallel Instances**, set **Minimum** to `2` or more. Keep **Maximum** at or above the minimum.
3. Select **Save Changes**.

{% hint style="info" %}

* This protects against planned maintenance only. It does not prevent downtime from unplanned failures, such as a server crash or an error in your Flow.
* Contextual applies the protection when you create, save, or start the Agent. Restarting an Agent that is already running does not apply it.
* **Parallel Instances** appears only if your plan allows more than one instance per Agent.
  {% endhint %}


---

# 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.contextual.io/documentation-and-resources/components-and-data/agents/types-of-agents/http-to-flow.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.