How to Implement A/B Testing with Claude Code

The Big Picture of A/B Test Implementation

A/B testing is essential for data-driven decision making. However, implementing correct statistical analysis, user bucketing, and result tracking from scratch is a big lift. With Claude Code, you can efficiently build a statistically sound A/B testing foundation.

Test Assignment Engine

> Build an engine that consistently assigns users to A/B groups.
> The same user should always get the same variant.

import crypto from 'crypto';

interface Experiment {
  id: string;
  variants: { id: string; weight: number }[];
}

class ABTestEngine {
  private experiments: Map<string, Experiment> = new Map();

  register(experiment: Experiment) {
    const totalWeight = experiment.variants.reduce((sum, v) => sum + v.weight, 0);
    if (Math.abs(totalWeight - 100) > 0.01) {
      throw new Error('Variant weights must sum to 100');
    }
    this.experiments.set(experiment.id, experiment);
  }

  assign(experimentId: string, userId: string): string {
    const experiment = this.experiments.get(experimentId);
    if (!experiment) throw new Error(`Experiment not found: ${experimentId}`);

    const hash = crypto
      .createHash('md5')
      .update(`${experimentId}:${userId}`)
      .digest('hex');
    const bucket = parseInt(hash.substring(0, 8), 16) % 100;

    let cumulative = 0;
    for (const variant of experiment.variants) {
      cumulative += variant.weight;
      if (bucket < cumulative) return variant.id;
    }
    return experiment.variants[0].id;
  }
}

// Usage example
const engine = new ABTestEngine();
engine.register({
  id: 'checkout-flow',
  variants: [
    { id: 'control', weight: 50 },
    { id: 'new-design', weight: 50 },
  ],
});

Using It in React Components

import { createContext, useContext, useEffect } from 'react';

function useExperiment(experimentId: string): string {
  const engine = useContext(ABTestContext);
  const userId = useCurrentUserId();
  const variant = engine.assign(experimentId, userId);

  useEffect(() => {
    trackEvent('experiment_exposure', {
      experimentId,
      variant,
      userId,
    });
  }, [experimentId, variant, userId]);

  return variant;
}

// Using it inside a component
function CheckoutPage() {
  const variant = useExperiment('checkout-flow');

  return variant === 'new-design'
    ? <NewCheckoutFlow />
    : <CurrentCheckoutFlow />;
}

Statistical Analysis of Results

To properly evaluate the results of an A/B test, you need to calculate statistical significance.

interface TestResult {
  sampleSize: number;
  conversions: number;
}

function calculateSignificance(control: TestResult, treatment: TestResult) {
  const p1 = control.conversions / control.sampleSize;
  const p2 = treatment.conversions / treatment.sampleSize;

  const pooledP = (control.conversions + treatment.conversions) /
    (control.sampleSize + treatment.sampleSize);

  const se = Math.sqrt(
    pooledP * (1 - pooledP) * (1 / control.sampleSize + 1 / treatment.sampleSize)
  );

  const zScore = (p2 - p1) / se;
  const pValue = 2 * (1 - normalCDF(Math.abs(zScore)));

  return {
    controlRate: (p1 * 100).toFixed(2) + '%',
    treatmentRate: (p2 * 100).toFixed(2) + '%',
    improvement: (((p2 - p1) / p1) * 100).toFixed(2) + '%',
    pValue: pValue.toFixed(4),
    significant: pValue < 0.05,
  };
}

function normalCDF(x: number): number {
  const a1 = 0.254829592, a2 = -0.284496736;
  const a3 = 1.421413741, a4 = -1.453152027;
  const a5 = 1.061405429, p = 0.3275911;
  const sign = x < 0 ? -1 : 1;
  x = Math.abs(x) / Math.sqrt(2);
  const t = 1.0 / (1.0 + p * x);
  const y = 1.0 - ((((a5 * t + a4) * t + a3) * t + a2) * t + a1) * t * Math.exp(-x * x);
  return 0.5 * (1.0 + sign * y);
}

Summary

With Claude Code, you can build a cohesive A/B testing foundation that covers everything from user bucketing to statistical significance calculations. For feature flag integration, see the feature flags implementation guide, and for analytics wiring, see the analytics implementation guide.

For the theory behind statistical testing, Evan Miller - Sample Size Calculator is a great reference.