Chain-of-Thought — let the model reason step by step
Ask the AI to think out loud and solve problems in steps to dramatically improve accuracy on reasoning tasks.
Reasoning4.8
Prompt template
Solve the problem below step by step. Show your reasoning for each step before giving the final answer, and clearly mark the final answer with 'FINAL ANSWER:'. Do not skip steps. Problem: [problem]
How to use
- 1Start with 'Let's work through this step by step'
- 2Ask for reasoning shown before the conclusion
- 3Require the final answer to be marked explicitly
- 4For math: ask to verify each calculation
Pro tips
- Works best on arithmetic, logic and multi-stage decisions
- Pair with few-shot examples for even better results
Works best with
ReasoningProblem SolvingMathAnalysis
Ratings & Reviews
Loading reviews…
Related Skills
Reasoning
Tree of Thoughts — deliberate problem solving with branching reasoning
Explore multiple reasoning paths simultaneously, evaluate each branch, and backtrack when a path leads to a dead end.
Tree of ThoughtsReasoningProblem Solving
4.1
Reasoning
Self-Consistency — sample multiple paths and vote on the answer
Generate several independent reasoning paths and select the answer that appears most frequently, reducing errors from single-path reasoning.
Self-ConsistencyEnsembleAccuracy
4.5
Agent
ReAct Prompting — reasoning + acting for tool-using agents
Alternate between Thought (reasoning) and Action (tool call) steps so the AI can solve multi-step tasks with external tools.
ReActAgentTool Use
4.6