Overview
The Developer Tools section is the technical home of ABsmartly. It covers every way you can integrate, automate, extend or operate the platform from code or AI tools — from running your first experiment in a web app to driving the entire system from a Claude or Cursor chat.
If you are an engineer integrating ABsmartly, a platform team maintaining experiment infrastructure, or a PM/analyst automating workflows, this section is for you.
What's in this section
SDK Guide
The SDK Guide is the starting point for any product integration. It explains how to install the client SDK, create a context, expose users to experiments and track goals — in all officially supported languages and frameworks.
Topics covered:
- Getting started — install the SDK and create your first context
- Running your first experiment — assign variants and use variant variables
- Targeting and audiences — restrict experiments by attribute
- Managing the context lifecycle — initialise, publish, refresh and finalise
- Pre-fetching context data — speed up first paint with server-side prefetch
- Checking variants without exposures — inspect treatments without logging an exposure
- Using variables as code — push HTML, CSS or JS from the Web Console
- Using custom fields — read custom experiment metadata from your code
Full end-to-end examples — covering JavaScript, React, Vue, Vue 3, Python, Java, Go, PHP, Ruby, Swift, .NET and Flutter — are embedded as language tabs in Running your first experiment.
SDK API
The SDK API reference documents the ABsmartly Collector API — the HTTP endpoints the SDKs talk to. Use this when you are building a custom integration in a language that doesn't have an official SDK, or when you need to inspect the raw protocol the SDKs use to fetch contexts and publish exposures.
It includes endpoints for context creation, exposure publishing (single and batch), experiment lookup and collector health checks.
Platform API
The Platform API is the full HTTP API behind the ABsmartly Web Console. Anything you can do in the UI you can do through the API: list and create experiments, manage metrics and goals, control teams and permissions, manage applications and unit types, post annotations and comments, fetch experiment results, and configure webhooks.
This is the right surface for:
- CI/CD automation (e.g. create experiments from a deploy pipeline)
- Custom dashboards and internal tooling
- Bulk imports/exports
- Programmatic governance — auditing experiments, metrics or permissions
See the API examples for end-to-end integrations such as a custom Slack notifier.
MCP Server
The MCP Server gives AI assistants — Claude, Cursor, VS Code Copilot, Windsurf, Gemini, ChatGPT — full access to the ABsmartly platform through a single connector. Drive experiments, metrics, goals and teams conversationally instead of by writing API calls.
Common starting points:
- Quick Start — connect Claude Desktop with OAuth in under five minutes
- Setup — every supported MCP client
- Usage Examples — natural-language prompts that work today
- Tools Reference — the full surface: 230+ commands across 33 groups
Which one should I use?
| If you want to… | Use |
|---|---|
| Assign variants and track goals in your application code | SDK Guide |
| Integrate ABsmartly in a language with no official SDK | SDK API |
| Create, manage or query experiments programmatically | Platform API |
| Build automation, internal tools, or CI/CD integrations | Platform API |
| Drive ABsmartly from Claude, Cursor or another AI assistant | MCP Server |
| Visually edit pages for an A/B test without writing code | LaunchPad browser extension |
| Run experiments and configure the workspace from the UI | Product Documentation |
The SDK and the APIs solve different problems and are commonly used together in the same product: the SDK does the user-facing work (assignment, exposure, goal tracking) while the Platform API is used by your internal tools and automation to configure and inspect experiments. The MCP Server sits on top of the Platform API — it's a conversational interface to the same operations.
New to ABsmartly?
If you are integrating the platform for the first time, the recommended path is:
- Read Get Started to understand the core concepts
- Follow Running your first experiment in the language of your choice
- Skim the Platform API introduction so you know what's available when you need it
- Try the MCP Server Quick Start if you'd like to drive ABsmartly from your AI assistant