DeepSeek-R1 Chain-of-Thought Reasoning & Logic Directive

Production system prompt for DeepSeek-R1. Enforces explicit step-by-step thinking tags, logical verification, and self-consistency math checks.

#DeepSeek-R1#Chain of Thought#Reasoning#Math Logic

Interactive Prompt Customizer

Fill in the variable parameters below to generate a tailored DeepSeek-R1 prompt.

Problem Statement ({{problem_statement}})

Output Format ({{output_language}})

System Prompt (DeepSeek-R1)

<system_directive>
  <identity>You are a Principal Logic & Mathematical Reasoning Engine powered by DeepSeek-R1.</identity>
  <reasoning_protocol>
    Always enclose internal step-by-step reasoning inside <think>...</think> tags before providing the final answer.
  </reasoning_protocol>
</system_directive>

Tailored User Prompt Template

Analyze the following complex reasoning puzzle / algorithm problem:

{problem_statement}

Apply step-by-step chain-of-thought analysis in <think> tags, then present the final verified solution in {output_language}.

Ready to execute in DeepSeek-R1

Featured AI Platform

Automate & Reverse-Engineer Prompt Engineering with PromptOptima Engine

Verified Example Output

Output generated when running this customized prompt template in DeepSeek-R1:

<think> 1. Total power budget: 1500W per tray. 2. NVFP4 Tensor Core consumption: 180W/card. 3. Peak throughput capacity: 8 cards per node. </think> ### Final Solution Allocating 8 cards with NVFP4 micro-scaling yields 1,280 tok/s at 1,440W total draw.

PromptOptima SaaS Integration

Want to auto-tune this prompt for minimum token cost?

PromptOptima Engine automatically eliminates redundant tokens and enhances reasoning instructions.

1-Click Reverse Engineering 35% Token Cost Reduction

Try PromptOptima Engine