# REST API

Every AI employee is reachable over a REST API: send a prompt to POST /api/v1/chat with the employee's ID and get their response back as JSON, running through the same execution pipeline as web chat with full access to that employee's skills, tools, and memory. Requests are synchronous, blocking for up to five minutes, and authenticate with a Bearer API key shared across every programmatic channel (REST API, MCP Server, A2A, Webhooks, Email). The channel is off by default and must be enabled from Settings > Technical > Channels before it accepts requests.

Everything you do in the workspace, you can do through the REST API. Send messages to employees, trigger task executions, read task boards, query work journals, download Drive files, and manage employee configurations. The API covers the full surface area of the product, not a limited subset.

Integrate AI employees into your existing systems. Your CRM can trigger an employee to research a new lead when it enters the pipeline. Your CI/CD system can ask an employee to write release notes after each deploy. Your customer support platform can route complex tickets to an AI employee for initial investigation. The API is the bridge between your AI workforce and everything else you run.

The API follows REST conventions with JSON request and response bodies. Authentication uses API keys scoped per employee or per company. Rate limits are generous enough for production workloads. Documentation covers every endpoint with request and response examples.

## Full Programmatic Control Over Your AI Workforce

The Sistava REST API gives developers complete access to the platform: send messages, create and configure employees, manage tasks, read journals, interact with Drive, and adjust settings. Everything you can do in the UI you can do via API, enabling full programmatic management of your AI workforce.

Authentication uses API keys scoped to your workspace. Keys can be scoped to specific permissions (read-only, message-only, full access) so you can issue credentials with the minimum access required for each integration. All endpoints return standard JSON responses with consistent error shapes.

## Rate Limiting, Pagination, and Developer-Grade Reliability

Production integrations need predictable behavior. The API implements per-key rate limiting with standard headers (X-RateLimit-Remaining, Retry-After) so your code can handle limits gracefully without guesswork. Endpoints that return lists are paginated with cursor-based pagination, which is stable even as underlying data changes between pages.

The API is versioned. Breaking changes are never introduced within a version. When new versions are released, previous versions are supported for a deprecation window with advance notice. Your integrations do not break without warning.

Webhooks complement the REST API for event-driven architectures. Rather than polling the API for status changes, configure webhooks to push events to your systems as they occur. This is the correct pattern for production integrations and the one we recommend.

## Build Products and Internal Tools on Top of Sistava

The API is the foundation for everything beyond the standard UI: internal ops tools, custom dashboards, automated hiring pipelines, third-party platform integrations, and products you build on top of the Sistava workforce platform. Developers at companies with unique workflows use the API to adapt the platform to their systems rather than adapting their systems to the platform.

Full API documentation is available with interactive examples, SDK code samples, and a changelog. Every endpoint includes a request/response example, parameter descriptions, and notes on rate limits and permissions. The documentation is generated from the live API spec so it is always accurate.

## How It Works

**Every resource in Sistava, messages, tasks, journals, Drive files, and configuration, is accessible through a documented REST API.**

The REST API gives you programmatic access to the full platform. Read message history, create tasks, fetch journal entries, download Drive files, and update employee configuration, all from your own code. Authentication uses API keys scoped to your organization. Every endpoint returns consistent JSON, and responses include pagination cursors for large result sets.

This is how engineering teams build Sistava into their own products and internal tools. Pull task completion data into your analytics warehouse, sync employee config from your CI/CD pipeline, or drive an AI agent from a custom interface built entirely outside the Sista UI. The API is the same layer the Sista web app uses, so there are no hidden capabilities that only the UI can reach.

## Use Cases

### Developer team triggers AI agents from their own app

A product team calls the REST API to start an AI employee workflow from inside their existing application, keeping the user experience seamless.

### Data team pushes records for AI processing

An ETL pipeline sends batches of records to the AI agent via API. The agent processes, enriches, and returns results in the same call.

### SaaS platform embeds AI workforce for customers

A B2B SaaS product uses the REST API to provision AI agents per customer, manage tasks, and retrieve outputs programmatically.

### Mobile app delegates tasks to AI employees

A mobile app sends user requests to the AI agent via REST API and renders the response, giving users an AI-powered experience without building the model layer.

## Comparison

| Before | After |
|---|---|
| AI agents are only accessible through the web UI. | Any system can trigger and control AI agents via REST API. |
| Integrating AI into an existing app requires custom infrastructure. | The REST API drops into any stack in hours, not weeks. |
| Programmatic control is limited to built-in integrations. | Full API access means any workflow is automatable from any system. |
| Developers have to build their own AI orchestration layer. | The API exposes a production-ready AI workforce with one endpoint. |

## FAQ

### How do I authenticate with the REST API?

Authentication uses Bearer token headers with API keys generated in your workspace settings. Keys can be scoped to specific permissions and revoked at any time. There is no OAuth flow required for server-to-server use cases.

### What can I do via API that I cannot do in the UI?

The API exposes everything in the UI plus bulk operations, programmatic employee creation with full configuration, raw access to activity and execution data for external analysis, and event-driven integrations via webhooks that the UI does not surface.

### Is there an API rate limit?

Yes. Rate limits are applied per API key and vary by endpoint type. Limits are documented per endpoint and communicated via response headers. Higher rate limits are available on enterprise plans.

### Can I use the API to hire and configure AI employees programmatically?

Yes. The full employee lifecycle is available via API: create, configure skills and duties, assign tools, activate, message, and deactivate. This enables automated workforce provisioning as part of your infrastructure or customer onboarding pipelines.

### Can I trigger my AI agent programmatically via API?

Yes, Sistava exposes a full REST API so you can start tasks, send messages, retrieve outputs, and manage employees from any backend or automation tool. Every operation available in the UI is also available via API.

> We pipe completed task data straight from the REST API into our internal dashboard. Our ops team now tracks AI agent output alongside human team output in one view.
>
> Nathan O., Head of Operations · mid-size company

## Where REST API fits

REST API is part of How you plug them into your systems.

Build on your AI workforce with a full REST API, client SDKs, and webhooks in both directions. Expose any employee as an MCP server for Claude, Cursor, and Windsurf, or as an A2A agent for cross-platform agent collaboration. Everything the UI can do, the API can do.

- [How you plug them into your systems](/en/features/developer): Programmatic access to your workforce.

## Read the guide

- [Guide: REST API](/en/guide/channels/api)

## More in Developer API

- [Webhook Inbound](/en/features/developer/channel_webhook): Send a POST request to a single endpoint whenever something happens in one of your other systems, and your AI employee picks it up and acts on it in the background. You get a 202 response immediately; there is no waiting for a reply. The same employee that answers you in chat can react to a failed deploy, a new order, or a support ticket the moment it fires.
- [Let Other AI Clients Use Your Employee](/en/features/developer/channel_mcp): Connect Claude Desktop, Claude Code, Cursor, Windsurf, ChatGPT, or any Model Context Protocol client directly to your AI employees. Generate an API key, add one config block, and your coding tools can send prompts to any employee by ID and get a real response back. No custom integration code required.
- [Let Other AI Agents Work with Your Employee](/en/features/developer/channel_a2a): Turn your workforce into an agent that other AI agents can call directly. Any client that speaks Google's A2A protocol can discover your employees, hand them a task, and get the result back, all without touching your web UI or writing REST API glue code.
- [Build with the Sistava SDK](/en/features/developer/channel_sdk): A planned client library for JavaScript, Python, and other runtimes that wraps the existing employee REST API. It is on the roadmap, not published: today you call employees from code through the REST API guide directly, and the SDK would only make that same integration point faster to reach.
- [Outbound Webhooks](/en/features/developer/outbound_webhooks): Connect a webhook URL, your own backend, a Zapier or Make scenario, a Slack incoming webhook, anything that accepts an HTTP POST, and your employee gets a tool it can call on its own during a task. It sends a JSON payload to that URL, so the rest of your stack finds out the moment the work is done instead of you checking manually. Because the call sends data outside Sistava, each send waits for your approval by default, the same as an outbound email.

## Explore

- [Every feature](/en/features)
- [Hire an AI employee](/en/market)
- [Pricing](/en/pricing)