> For the complete documentation index, see [llms.txt](https://docs.spara.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.spara.com/agents/channels/configuring.md).

# Configuring Channels

Every [Channels](/agents/channels.md), whether [Chat](/agents/channels/chat.md), [Email](/agents/channels/email.md), [Phone](/agents/channels/phone.md), [SMS](/agents/channels/sms.md), or [Product Demo](/agents/channels/product-demo.md), is built and run the same way. You write its instructions, give it abilities, test a draft, and publish when it's ready. The pages here cover those shared building blocks once, so each channel page can focus on what's specific to its channel.

<figure><img src="/files/TvcmJ7olkziAD4EStMAr" alt=""><figcaption><p>Every channel is built in the same split-screen editor: instructions on the left, testing on the right.</p></figcaption></figure>

| Building block                                                               | What it does                                                                                                           |
| ---------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- |
| [AI Instructions](/agents/channels/configuring/ai-instructions.md)           | The natural-language prompt that defines how the channel behaves.                                                      |
| [Abilities](/agents/channels/configuring/abilities.md)                       | Tools the channel can use mid-conversation (calendar, transfer, media, and more).                                      |
| [Testing](/agents/channels/configuring/testing.md)                           | A built-in interface and automated [Testing](/agents/channels/configuring/testing.md#simulations) to validate a draft. |
| [Ask Spara AI](/agents/channels/configuring/ask-spara-ai.md)                 | An assistant that analyzes and rewrites your instructions.                                                             |
| [Saving & Publishing](/agents/channels/configuring/saving-and-publishing.md) | A private draft and a single live version per channel.                                                                 |
| [A/B Testing](/agents/channels/configuring/a-b-testing.md)                   | Duplicate a channel into variants and split traffic to optimize conversion.                                            |

Not every channel supports every ability. Chat and Phone have the richest toolsets, while Email and SMS operate on text alone. Each channel page covers what's specific to that channel.

## The lifecycle

The same loop applies to every channel:

1. **Write** its [AI Instructions](/agents/channels/configuring/ai-instructions.md) and configure its [Abilities](/agents/channels/configuring/abilities.md).
2. **Test** the draft in the built-in interface or with automated [Testing](/agents/channels/configuring/testing.md), using [Ask Spara AI](/agents/channels/configuring/ask-spara-ai.md) to diagnose and refine.
3. **Publish** when you're satisfied. See [Saving & Publishing](/agents/channels/configuring/saving-and-publishing.md). Leads only ever interact with the published version.
4. **Optimize** by running an [A/B Testing](/agents/channels/configuring/a-b-testing.md) between variants.

## Knowledge and analytics

Two more things are shared by every channel, with no per-channel setup required:

* **Knowledge**: channels draw on your [Knowledge](/platform/knowledge.md) base (scraped webpages, uploaded documents, key questions) to answer factual questions about your product.
* **Analytics**: every channel automatically tracks its conversion metrics in [Analytics](/platform/analytics.md).


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.spara.com/agents/channels/configuring.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.