Agentic AI Reference Architecture

Cognition · Data artifact

Zero-Shot CoT Prompt

Data artifactCognitionCognition & Memoryarc:ZeroShotCoTPrompt

A chain-of-thought prompt that supplies no demonstrations, only a reasoning trigger instruction (e.g., "Let's think step-by-step") appended to the problem.

Responsibility. Triggers self-structured step-by-step reasoning without examples.

Also known as: Reasoning trigger, Zero-shot Chain-of-Thought

Variant of Chain-of-Thought Prompt abstract

When to choose. Choose when immediate deployment is needed across diverse, unpredictable problem types without time or budget to craft examples, accepting variable reasoning quality on ambiguous problems.

specializesis target of alternativeTois read byis target of alternativeToChain-of-Thought Prompt: specializesChain-of-Thought PromptAuto-CoT Prompt: is target of alternativeToAuto-CoT PromptCoT Rationale Generator: is read byCoT Rationale GeneratorFew-Shot CoT Prompt: is target of alternativeToFew-Shot CoT Prompt
Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

alternative to variability

Design guidance

Classification

Patterns
Zero-shot CoT
Quality attributes
Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)Maintainability (ISO/IEC 25010)

Sources

  1. Ch5.1: T. Nguyen, "Chain-of-Thought (CoT) Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.1. ISBN: 9798244538229.
  2. Ch10.1: T. Nguyen, "Conversational UI," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.1. ISBN: 9798244538229.