Agentic AI Reference Architecture

Cognition · Data artifact

Auto-CoT Prompt

Data artifactCognitionCognition & Memoryarc:AutoCoTPrompt

A chain-of-thought prompt whose demonstrations are automatically generated (clustered representative questions with zero-shot CoT rationales) and matched to each incoming question.

Responsibility. Supplies automatically generated, question-matched reasoning demonstrations.

Also known as: Automatic Chain-of-Thought prompt

Variant of Chain-of-Thought Prompt abstract

When to choose. Choose when many distinct problem types need structured reasoning but resources are insufficient to hand-craft examples for each, or when the question distribution is unknown or evolving; accept added pipeline complexity and slightly lower quality than hand-crafted few-shot.

specializesis written byalternative toalternative toChain-of-Thought Prompt: specializesChain-of-Thought PromptSimilarity Exemplar Selector: is written bySimilarity Exemplar Sele…Zero-Shot CoT Prompt: alternative toZero-Shot CoT PromptFew-Shot CoT Prompt: alternative toFew-Shot CoT Prompt
Direct neighbourhood (hover for relationship types)

Relationships

is written by dependency

alternative to variability

Design guidance

Classification

Patterns
Auto-CoTCluster-then-bootstrap demonstration generation
Technologies
Sentence transformer models
Quality attributes
Performance efficiency (ISO/IEC 25010)Maintainability (ISO/IEC 25010)Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)
Risks mitigated
Manual demonstration authoring bottleneckOverfitting to a single reasoning template

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.