All Tools/CampaignsWrite

Launch Experiment

Launch an A/B experiment on a campaign to compare variant performance using SPRT (Sequential Probability Ratio Test) for statistical significance. Campaign must have at least 2 step variants. Metric can be acceptance_rate or reply_rate. Pure DB operation with no LinkedIn API calls.

MCP tool name: launch_experiment

Use Cases

Test two connection note variants to maximize acceptance rate
Compare follow-up message styles for reply rate
Run statistically rigorous experiments instead of guessing

Parameters

Name	Type	Required	Description
campaign_id	`string`	required	Campaign UUID or slug with 2+ variants
name	`string`	required	Human-readable experiment name
metric	`string`	optional	acceptance_rate (default) or reply_rate
min_samples_per_variant	`number`	optional	Min samples before SPRT acts (default 100)
min_days	`number`	optional	Min days before SPRT acts (default 7)

Example

Prompt

Launch an A/B test on my GTM campaign comparing the two connection note variants

Response

{
  "success": true,
  "experiment_id": "uuid-123",
  "variants": 2,
  "metric": "acceptance_rate"
}

Permission Scopes

This tool is available in the following permission scopes:

full accessoutboundcontent

Related Tools

Get Experiment Results

Check A/B experiment status, per-variant stats, SPRT decision, winner assessment with confidence and lift via MCP.

Promote Experiment Winner

Apply the winning variant to your campaign so all future sends use the best-performing copy via MCP.

Explore all Outreach tools

The complete LinkedIn API. Ready when you are.

Connect your first LinkedIn profile in under 5 minutes. All 160 tools. Safe limits, warm-up, and full permission control built in.

Start now Read the docs