# Explicit criteria to cut false positives

*Claude Certified Architect - Foundations Study Guide · Prompt Engineering & Structured Output · Last updated October 22, 2026 · https://www.certifyforce.com/study-guide/claude-certified-architect-foundations/prompt-engineering-and-structured-output/explicit-criteria-to-cut-false-positives*

Why vague review and classification instructions such as "be conservative" or "only report high-confidence findings" fail, and how categorical report/skip lists, severity definitions with code examples, evidence rules, REVIEW.md and a labeled evaluation set raise precision without hiding real issues.

- Certification: Claude Certified Architect - Foundations
- Exam section: Prompt Engineering & Structured Output
- Study guide: https://www.certifyforce.com/study-guide/claude-certified-architect-foundations

**Official exam objective:**

> Design prompts with explicit criteria to improve precision and reduce false positives

## What the exam expects

- Replace a vague instruction ("check that comments are accurate", "flag anything unusual", "escalate urgent tickets") with a categorical criterion that says exactly which findings to report and which to skip.
- Explain why "be conservative", "only report high-confidence findings" and confidence-score thresholds fail to raise precision, and reject them as distractors.
- Restore developer trust by temporarily disabling a high false-positive category while its criteria are rewritten, keeping accurate categories running.
- Define severity levels with explicit criteria and a concrete code example per level so classification stays consistent across runs.
- Require evidence for a class of finding, tune managed Code Review with a committed `REVIEW.md`, and prove a new prompt on a labeled set before rollout.

Key terms: **precision** (share of reported findings that are real); **recall** (share of real issues that get reported); **false positive** (a reported finding that is not a real problem); **categorical criterion** (a rule naming the issue types to report or skip, not a confidence level); **`REVIEW.md`** (repository-root file of review-only instructions for Code Review).

## Key facts

| Fact | Detail | Source |
|---|---|---|
| "Be conservative" / "high-confidence only" | Do not improve precision compared with specific categorical criteria | [Exam guide](https://everpath-course-content.s3-accelerate.amazonaws.com/instructor%2F6nizmqk8tpzpfjvt6qmmav7rh%2Fpublic%2F1783542750%2FClaude+Certified+Architect+%E2%80%93+Foundations+Exam+Guide.pdf) |
| Noisy category | Temporarily disable it to restore trust while its prompt is improved | [Exam guide](https://everpath-course-content.s3-accelerate.amazonaws.com/instructor%2F6nizmqk8tpzpfjvt6qmmav7rh%2Fpublic%2F1783542750%2FClaude+Certified+Architect+%E2%80%93+Foundations+Exam+Guide.pdf) |
| Consistent severity | Explicit criteria plus a concrete code example per level | [Exam guide](https://everpath-course-content.s3-accelerate.amazonaws.com/instructor%2F6nizmqk8tpzpfjvt6qmmav7rh%2Fpublic%2F1783542750%2FClaude+Certified+Architect+%E2%80%93+Foundations+Exam+Guide.pdf) |
| `REVIEW.md` location | Repository root, read from the base or default branch, never the PR's changes | [Customize Code Review](https://code.claude.com/docs/en/code-review-customize) |
| Protected default branch | Severity lowering, exclusions and nit caps from the root file are honored | [Customize Code Review](https://code.claude.com/docs/en/code-review-customize) |
| Wrong-finding fix | Require `file:line` evidence, not inference from naming | [Customize Code Review](https://code.claude.com/docs/en/code-review-customize) |
| Success criteria | Specific and measurable; precision and recall are generic metrics | [Define success criteria](https://platform.claude.com/docs/en/test-and-evaluate/develop-tests) |

## Check yourself

- Why does appending "be conservative" to "flag anything unusual" barely change the false positive rate?
- When should you turn off a whole review category?
- Why is mapping severity to Claude's confidence a poor design?
- How do you show a rewritten prompt cuts false positives without hiding real bugs?

## Sources

- [Claude Certified Architect – Foundations Exam Guide v1.0](https://everpath-course-content.s3-accelerate.amazonaws.com/instructor%2F6nizmqk8tpzpfjvt6qmmav7rh%2Fpublic%2F1783542750%2FClaude+Certified+Architect+%E2%80%93+Foundations+Exam+Guide.pdf)
- [Prompting best practices](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices)
- [Customize Code Review](https://code.claude.com/docs/en/code-review-customize)
- [Read and request reviews on a pull request](https://code.claude.com/docs/en/code-review-pull-requests)
- [Define success criteria and build evaluations](https://platform.claude.com/docs/en/test-and-evaluate/develop-tests)
- [Increase output consistency](https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/increase-consistency)

## About the full unit

The "Core concepts", "Exam traps" and "Worked scenario" sections of this unit, its 9 linked practice questions, and unlimited timed mock exams are included with the Claude Certified Architect - Foundations pack (USD $19): https://www.certifyforce.com/practice-exams