Skip to content
GET/api/v1/prompts/ab-experiments/{id}

A/B experiment detail with live significance

Returns { experiment, variants, liveSignificance, totals }. liveSignificance is recomputed from current samples on every request (null when the experiment has fewer than 2 variants): a two-proportion z-test for metric=pass_rate, otherwise Welch's t-test on the top two variants by mean. Its `winnerId` is null until BOTH OF THE TOP TWO variants reach min_samples (a third arm with no samples does not hold the decision back) (winner_config.min_samples, default 30) and the p-value falls below 1 − confidence (default 0.95); direction defaults to lower_is_better for latency/cost and higher_is_better otherwise. The stored decision remains on experiment.winner_variant_id. totals sums runs and passed across variants. Requires the Pro plan; org membership is resolved from the experiment row.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.

Parameters

id in pathrequired
string

Response

200 example

{
  "success": true
}

All status codes

200Detail + significance.
400(no description)
401(no description)
403Forbidden — the credential is valid but lacks the API-key scope, member role, or plan entitlement this operation requires.
404(no description)
409Conflict — CONFLICT.
429(no description)
500Internal Server Error — DB_ERROR.

Code samples

cURL

# {id} is shown with an EXAMPLE value — replace it with real values.
curl -X GET \
  https://evalguard.ai/api/v1/prompts/ab-experiments/00000000-0000-0000-0000-000000000000 \
  -H "Authorization: Bearer $EVALGUARD_API_KEY"

TypeScript

// The TypeScript SDK (@evalguard/sdk) exposes TYPED methods — runEval,
// getEval, runSecurityScan, checkFirewall, … — not a generic request().
// For an arbitrary endpoint, call it directly:
// {id} is shown with an EXAMPLE value — replace it with real values.

const res = await fetch("https://evalguard.ai/api/v1/prompts/ab-experiments/00000000-0000-0000-0000-000000000000", {
  method: "GET",
  headers: { Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}` },
});
console.log(res.status, await res.json());

Python

# The Python SDK (pip install evalguardai) exposes TYPED methods on
# EvalGuardClient — run_eval, get_eval, … — not a generic request().
# For an arbitrary endpoint, call it directly:
# {id} is shown with an EXAMPLE value — replace it with real values.

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['EVALGUARD_API_KEY']}"}

response = requests.request("GET", "https://evalguard.ai/api/v1/prompts/ab-experiments/00000000-0000-0000-0000-000000000000", headers=headers)
print(response.status_code, response.json())

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
)

// {id} is shown with an EXAMPLE value — replace it with real values.
func main() {
	req, _ := http.NewRequestWithContext(context.Background(), "GET", "https://evalguard.ai/api/v1/prompts/ab-experiments/00000000-0000-0000-0000-000000000000", nil)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403404409429500

Other Prompts endpoints