> For the complete documentation index, see [llms.txt](https://help.blotato.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.blotato.com/start-with-an-ai-agent.md).

# Start with an AI agent

- [Start here](https://help.blotato.com/start-with-an-ai-agent/agents.md): Route a customer task or support question by surface, client, platform, artifact, and stage.
- [Diagnose a support question](https://help.blotato.com/start-with-an-ai-agent/agent-triage.md): Diagnose customer questions by client, surface, artifact, failing stage, prior attempts, and verified outcome.
- [Find a post's outcome before retrying](https://help.blotato.com/start-with-an-ai-agent/publishing-status.md): Diagnose missing, delayed, duplicated, or failed posts without assuming an outage or resubmitting an unresolved request.
- [MCP Server](https://help.blotato.com/start-with-an-ai-agent/mcp.md): Connect the exact AI client, verify authentication with a read-only call, and select a supported task.
- [Connect your client](https://help.blotato.com/start-with-an-ai-agent/mcp/setup.md): Client-specific MCP configuration and authorization for Claude, Codex, ChatGPT, Cursor, VS Code, and other clients.
- [Tools reference](https://help.blotato.com/start-with-an-ai-agent/mcp/tools.md)
- [MCP input index](https://help.blotato.com/start-with-an-ai-agent/mcp/inputs.md)
- [Example prompts](https://help.blotato.com/start-with-an-ai-agent/mcp/examples.md): Map customer prompts to MCP workflows while preserving draft-only intent, destination approval, upload bytes, and completion checks.
- [MCP FAQs](https://help.blotato.com/start-with-an-ai-agent/mcp/faqs.md): Troubleshoot AI-client connections, authentication, uploads, and Blotato tool calls.
- [REST API quickstart](https://help.blotato.com/start-with-an-ai-agent/start.md): Configure REST authentication, connect social accounts, and verify access before publishing or building an automation.
- [Search and read help](https://help.blotato.com/start-with-an-ai-agent/docs-search.md): Search and read published Blotato help through the documentation MCP endpoint, separately from account access and publishing tools.
- [API reference for agents](https://help.blotato.com/start-with-an-ai-agent/llm.md)
- [Connection and endpoint index](https://help.blotato.com/start-with-an-ai-agent/llm/overview.md): Choose MCP or REST, verify authentication with a read-only request, and find the supported operations.
- [Account lookup](https://help.blotato.com/start-with-an-ai-agent/llm/accounts.md): Resolve REST account, Page, board, and playlist IDs without guessing a publishing destination.
- [Publishing requests](https://help.blotato.com/start-with-an-ai-agent/llm/publishing.md): Build a REST publishing request with platform-specific fields, choose one scheduling method, and verify the saved submission.
- [Visual generation requests](https://help.blotato.com/start-with-an-ai-agent/llm/visuals.md): Select a template schema, create an authorized visual, and verify finished media without repeating a paid job.
- [Source extraction requests](https://help.blotato.com/start-with-an-ai-agent/llm/sources.md): Submit REST source extraction with an explicit source type and stop on completed or failed results.
- [Schedules and slots](https://help.blotato.com/start-with-an-ai-agent/llm/scheduling.md): Read, edit, and cancel existing schedules, distinguish UTC slots from queued posts, and preserve user-approved content.
- [Comment requests](https://help.blotato.com/start-with-an-ai-agent/llm/comments.md): Read Instagram and Facebook comments, resolve Blotato post and parent-comment IDs, and verify an authorized reply.
- [Message requests](https://help.blotato.com/start-with-an-ai-agent/llm/messages.md): Resolve Instagram or Facebook message recipients, respect messaging windows, and verify an authorized send without duplicates.
- [DM automation requests](https://help.blotato.com/start-with-an-ai-agent/llm/automations.md): Create a draft DM automation, activate only on request, target tracked posts, and diagnose runs without duplicate sends.
- [Plan and request limits](https://help.blotato.com/start-with-an-ai-agent/llm/limits.md): Distinguish plan defaults, account-specific contact limits, upload constraints, and API request rate limits.
- [Workflow and common mistakes](https://help.blotato.com/start-with-an-ai-agent/llm/workflow.md): Choose only the requested REST operations, preserve asynchronous IDs, and verify results without duplicate writes.
- [API FAQs](https://help.blotato.com/start-with-an-ai-agent/faqs.md): Integration answers for authentication, publishing, uploads, visual generation, and errors.


---

# 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://help.blotato.com/start-with-an-ai-agent.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.
