> For the complete documentation index, see [llms.txt](https://aphid-ai.gitbook.io/aphid-ai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://aphid-ai.gitbook.io/aphid-ai-docs/aphid-api/api-overview.md).

# API Overview

#### Aphid Platform Overview

Aphid is positioned as an AI automation and agent orchestration layer. It sits between users, business workflows, enterprise data, and third-party systems. Aphid can understand a request, break it into steps, select the correct tools, retrieve the required context, execute approved actions, and report results back to the user or system.

* Conversational AI interface for users, operators, and administrators.
* Agent orchestration layer for planning, reasoning, task execution, and tool selection.
* API gateway and integration layer for external systems.
* MCP tool layer for standardized access to tools, files, databases, and services.
* Workflow automation engine for multi-step business processes.
* Security, policy, and audit framework for governed execution.
* Knowledge and retrieval layer for documents, records, embeddings, and system context.

| <p>Core Value Proposition<br>Aphid allows a company to connect its existing tools and convert business intent into secure action. Instead of simply answering questions, Aphid can complete approved work across systems.</p> |
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

<br>

#### API Capability Summary

| Capability                       | Description                                                                               | Business Use Case                                                                                                      |
| -------------------------------- | ----------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- |
| Authentication and authorization | OAuth 2.0, API keys, service accounts, role-based access, and scoped tokens.              | Control what each agent, user, or integration is allowed to access or execute.                                         |
| REST API integration             | Standard HTTP endpoints for reading, writing, updating, and triggering external systems.  | Connect to CRMs, ERPs, HR systems, ticketing platforms, finance systems, and custom applications.                      |
| Webhook ingestion                | Receive real-time events from third-party platforms.                                      | Trigger agents when a lead arrives, ticket changes, shipment updates, document is uploaded, or payment status changes. |
| Outbound webhooks                | Notify external systems when Aphid completes a task or reaches a workflow state.          | Send status updates, completion events, exceptions, or approval requests.                                              |
| MCP integration                  | Expose third-party tools and data sources as standardized model-callable tools.           | Allow Aphid agents to use tools safely without custom logic for every system.                                          |
| Agent task execution             | Agents can plan and execute multi-step tasks with policy constraints and approval gates.  | Automate research, reporting, support operations, system updates, and cross-platform workflows.                        |
| Data retrieval and RAG           | Retrieve knowledge from documents, records, databases, and APIs.                          | Answer questions using current enterprise context and source data.                                                     |
| Audit and observability          | Log user request, agent reasoning summary, tool calls, system actions, and final outcome. | Support compliance, troubleshooting, and governance reviews.                                                           |