Killswitches, configs, A/B tests, and auto-collected metrics — spun up from a single sentence. The platform that lives inside your conversation.
Scroll. The panel pins, the demo morphs.
{
"max_uploads": 100,
"model": "opus-4.1",
"enable_v2": true,
"region": "us-east-1"
}Every flag is a killswitch. Pull it manually, or set a guardrail — error rate, p95 latency, spend — and Shipeasy yanks it for you.
Typed runtime configs targeted by user, plan, geo, or anything you send. Edit from Claude, the dashboard, or a PR.
Sequential stats mean you can peek whenever you want without inflating false positives. Auto-ramping, SRM detection, guardrails — Claude writes the wrapper.
Activation, retention, revenue, and error rate are instrumented from day one. Add custom metrics with one line of code.
One command. Claude picks up the server, discovers your codebase, and registers four tools.
In plain English, tell Claude what you want to try. It writes the wrapper, picks the metric, and ramps safely.
Live metrics stream to the dashboard. Claude pings you when there's a clear winner — or when something breaks.
Sequential stats call it; Shipeasy ramps the winning variant from 25% to 100% over 48h on the guardrail of your choice.
One command — claude mcp add shipeasy — registers four tools with Claude. We use your project context to wire experiments into the right files. No YAML.
Both. Hosted is the default. Self-hosted is a one-binary deployment on Enterprise with full parity and an air-gapped mode.
Sequential testing by default — peek whenever, without inflating false positives. Bayesian and frequentist are available per-experiment.
Every action is reversible and logged. Killswitches and experiment changes go through a PR or a tool call you can undo.
JS/TS, Python, Go, Ruby, Rust, Swift. The SDK is a thin client; the heavy lifting happens server-side.
Install in 12 seconds. Your first experiment before your coffee is cold.