Back to Skills Library
BenchmarkingCompetitive AnalysisMetricsAI Agent Skill

ab-testing

Comparative feature testing, experimental teardowns, and defensibility benchmarks.

coreyhaines31/marketingskills
48.5k stars
48.5k installs
Updated: 2026-06-15

Install Options

Install into Claude Code, Cursor, Codex, or Antigravity with:

$ npx skills add coreyhaines31/marketingskills@ab-testing

Real Work Situation Solved

Deconstruct a competitor's AI feature without falling for marketing hype

A competitor announced a "100% Autonomous AI Agent" - how do you reverse-engineer what's real under the hood?

5-Step Action Framework

  1. 1Test adversarial edge cases, malformed inputs, and out-of-domain requests to find where the system breaks.
  2. 2Observe latency and rendering patterns: streaming implies an LLM call; instant response implies caching or rule-based logic.
  3. 3Determine whether the feature relies on proprietary model training or is simply a thin prompt wrapper around a commodity LLM API.
  4. 4Identify human-in-the-loop boundaries: where the workflow pauses for manual user confirmation.
  5. 5Compile a 4-factor matrix: core user problem solved, observed real-world accuracy, estimated unit cost, and actual defensibility.
Before

"The competitor's AI looks revolutionary, we must copy it immediately."

After

"Live teardown: feature is a simple prompt wrapper on GPT-4o with 6s latency that fails 4/10 numeric tasks. Proposal: solve with local rule engine in 50ms instead of blind imitation."

Related Course Lesson

AI Product ManagementLesson 8

Go to Lesson

SKILL.md Source Instructions

SKILL.md • Read-only preview
# A/B Testing & Teardown Skill

Run head-to-head capability evaluations comparing baseline implementations against competitors.