---
name: tai-theme-anti-patterns-and-the-new-quality-role
description: 'Use the Testing AI theme Anti-Patterns and the New Quality Role to plan, review, or teach related AI quality work. Applies concepts and techniques from the book to testing AI, AI-generated software, and non-deterministic systems when relevant.'
---

# Anti-Patterns and the New Quality Role

Skill name: `tai-theme-anti-patterns-and-the-new-quality-role`

Based on **Testing AI: Engineering Confidence in AI Systems** by **Jason Arbon**.

## Theme Purpose

Use these approaches when reviewing teams, metrics, test plans, bug workflows, pass/fail thinking, judge misuse, and the role of the AI quality engineer.

Apply these concepts when testing AI, AI-generated software, model-backed features, agents, search, chatbots, RAG systems, generated code, dynamic interfaces, or other software whose behavior can vary across runs, users, data, tools, or time.

## How To Use This Theme

- Identify the behavior, capability, risk, or release decision being evaluated.
- Choose the relevant concepts below and turn them into concrete eval cases, samples, traces, checks, rubrics, metrics, or release gates.
- Prefer evidence that supports a decision: ship, canary, hold, rollback, or collect more samples.
- Report by slices and severe failures when averages hide risk.
- Preserve enough evidence that another person or agent can understand what was tested, how it was measured, and why the recommendation follows.

## Concepts And Techniques To Apply

- Call out misleading patterns: boolean pass/fail, percent-passed scoreboards, over-specific test cases, golden-answer fixation, and one-run demos.
- Avoid filing every bad output as a normal bug when the real problem is distributional behavior that requires measurement and tuning.
- Do not treat aggregate scores, refusals, or LLM judge output as complete evidence.
- Evaluate the full path, not only the final answer.
- Prefer quality engineers who can combine automation, statistics, AI tools, coding agents, creativity, domain judgment, and release evidence.
- Treat quality evidence as part of the product and engineering workflow, not a late QA artifact.

## Reporting Guidance

- State what was tested and what population the evidence represents.
- Explain uncertainty, missing coverage, severe failures, and known blind spots.
- Connect findings to a concrete decision or next action.
- Use topic-specific chapter skills only when deeper detail is needed; this theme skill should stand alone as practical guidance.