# Customer.io Documentation
> Customer.io is a messaging automation platform for sending targeted email, push notifications, SMS, in-app messages, and webhooks based on customer behavior and data attributes. These docs cover setup, integration, messaging, segmentation, analytics, API reference, and agent-native access through the Customer.io CLI or MCP server.
## When to use this documentation
Customer.io decides who gets a message, what it says, and when it sends. Read these docs when the task in front of you is one of these:
- [Send a message from your own code](https://docs.customer.io/messaging/send/transactional/api.md): Transactional email, push, SMS, and WhatsApp. These are the messages you address to one person and trigger yourself.
- [Get profile and event data in](https://docs.customer.io/integrations/data-in/getting-started.md): Identify people, record what they do, and relate them to objects like accounts or carts.
- [Build something that sends on its own](https://docs.customer.io/messaging/send/automations/overview.md): Automations that react to an event, a segment, or a schedule without you calling an API each time.
- [Add Customer.io to a mobile or web app](https://docs.customer.io/integrations/sdk.md): The iOS, Android, React Native, Flutter, and JavaScript SDKs, including push and in-app messages.
- [Send delivery and engagement data somewhere else](https://docs.customer.io/integrations/data-out/getting-started.md): Reporting webhooks, warehouse syncs, and the destinations Data Pipelines writes to.
- [Work out which API to call](https://docs.customer.io/integrations/api/customerio-apis.md): What the Track, App, and Data Pipelines APIs each do, and which one a given task belongs to.
### How to read these docs
- Add `.md` to any documentation URL to get its Markdown source: `https://docs.customer.io/get-started/quick-start-guide.md`. Requesting a page with `Accept: text/markdown` redirects to the same thing.
- Pages with tabbed examples, such as one per language, platform, or database, take `?tab=<name>` to return only that tab. Repeat it to narrow several tab groups at once: `https://docs.customer.io/integrations/sdk/ios/quick-start-guide.md?tab=objective-c&tab=uikit-with-objective-c`. Each tabbed page lists its tab names at the top of its Markdown.
- Every section below has its own `llms.txt` naming each page in it, so you can read one area without loading the whole site.
- [`/openapi.json`](https://docs.customer.io/openapi.json) describes the Track and App APIs together, with the base URL each path answers on. [`/.well-known/api-catalog`](https://docs.customer.io/.well-known/api-catalog) lists every OpenAPI description this site publishes.
- A request for a page that does not exist answers `Accept: application/json` with a structured error carrying a code, a message, and links back to these indexes.
Customer.io documentation is organized into the following sections. Each section has its own `llms.txt` file with detailed page listings.
## Sections
- [AI features](https://docs.customer.io/ai/llms.txt): AI features documentation (23 pages)
- [Get started](https://docs.customer.io/get-started/llms.txt): Get started documentation (10 pages)
- [Integrations](https://docs.customer.io/integrations/llms.txt): Integrations documentation (798 pages)
- [Messaging](https://docs.customer.io/messaging/llms.txt): Messaging documentation (360 pages)
- [Settings & billing](https://docs.customer.io/accounts/llms.txt): Settings & billing documentation (40 pages)
## Additional resources
- [Customer.io CLI](https://docs.customer.io/ai/cli/get-started.md): Install the `customerio/cli` agent skill and let terminal-based coding agents sign up, authenticate, and manage Customer.io workspaces
- [Customer.io MCP](https://docs.customer.io/ai/mcp/get-started.md): Connect chat-based AI tools like ChatGPT and Claude Desktop to Customer.io
- [Full documentation](https://docs.customer.io/llms-full.txt): Complete text of all documentation pages in a single file
- [Customer.io API spec](https://docs.customer.io/openapi.json): Primary OpenAPI spec for the Track (ingress), App, and Design Studio APIs together, at the conventional path
- [Pipelines API spec](https://docs.customer.io/files/pipelines.json): OpenAPI spec for the Data Pipelines API
- [Track API spec](https://docs.customer.io/files/journeys-track.json): OpenAPI spec for the Track API
- [App API spec](https://docs.customer.io/files/journeys-app.json): OpenAPI spec for the App API
- [Design Studio API spec](https://docs.customer.io/files/design-studio.json): OpenAPI spec for the Design Studio API
- [Webhooks spec](https://docs.customer.io/files/journeys-webhooks.json): OpenAPI spec for reporting webhooks
Measured from the saved file
Linked document
UTF-8 text size
4.6 KB4743 bytes
Token count
1088o200k_base encoding
Markdown links
2221 distinct URLs
Fenced code blocks
044 lines in the file
Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.
Project H1
Customer.io Documentation
Opening blockquote
Customer.io is a messaging automation platform for sending targeted email, push notifications, SMS, in-app messages, and webhooks based on customer behavior and data attributes. These docs cover setup, integration, messaging, segmentation, analytics, API reference, and agent-native access through the Customer.io CLI or MCP server.
Context architecture
How the content is divided
3 H2 sections organize 22 parsed Markdown links. 8 links point to .md or .markdown paths; 0 link occurrences use another hostname. Linked destinations have not been recursively validated.
H2 section
Links
UTF-8 bytes
Tokens
When to use this documentationLine 5
8
2616
604
SectionsLine 26
5
508
122
Additional resourcesLine 34
9
1184
284
Nested indexes
5 distinct links point to other llms.txt paths. These are routes to more indexes, not proof their contents were included in this file.
Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.
Embedded material
Code, installation and API examples
Fenced blocks
0 closed
Declared languages
No fenced blocks detected
Package-install commands
0 detected in fenced or inline code
Authentication examples
0 fenced lines match API-key, Authorization, Bearer, OAuth or access-token patterns
HTTP request examples
0 fenced lines match request-method patterns
Authentication links
0 links have authentication-related labels
Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.
Publisher prioritization
The Optional section
No H2 section named “Optional” was detected in this file.
The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.
Machine-readable routes
MCP references and configuration text
MCP-related text was detected in the captured file. 1 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.
Bounded prefix inspected; the whole body was not downloaded
A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.
Change evidence
What can be said about freshness
This capture establishes a baseline. Update frequency cannot be determined from one observation.
File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.
Counts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.