🧪TDD Challenge·intermediate·⏱️ 30–45m·⭐ 200 XP
M-017Chain-of-Thought Math Solver
Description
Nebula Corp's educational platform needs a math tutoring system that doesn't just give answers — it shows the reasoning process. Students learn better when they see each step. The current prompt just asks for the answer, and the model often makes arithmetic errors on multi-step problems. Build a Chain-of-Thought prompt that forces the model to show its work step-by-step, verify the answer, and catch its own mistakes before presenting the final result.
Test Cases (6)
Includes step-by-step instruction
Must explicitly instruct the model to show reasoning steps
Input:"A train travels 60 mph for 2 hours, then 80 mph for 1.5 hours. How far did it travel?"
Expected:CONTAINS_ANY:step-by-step,step by step,show your work,think step
Includes the problem
The prompt must include the actual problem to solve
Input:"Sarah has 3 boxes with 8 crayons each. How many crayons total?"
Expected:CONTAINS:Sarah has 3 boxes with 8 crayons each
Requests identification of given info
Should ask the model to identify what information is provided
Input:"A rectangle is 12 feet long and 8 feet wide. What is its perimeter?"
Expected:CONTAINS_ANY:given,known,identify,what we need
Requests solution planning
Should ask the model to plan the solution approach
Input:"Tom has $50. He buys 3 books at $12 each. How much money is left?"
Expected:CONTAINS_ANY:plan,approach,operations,formulas,order
Requests verification
Should include a verification step to catch errors
Input:"A garden is 15m x 10m. What is its area in square meters?"
Expected:CONTAINS_ANY:verify,check,makes sense,alternative method,reasonable
Requests final answer
Should explicitly request a clearly stated final answer
Input:"Calculate 15% tip on a $80 restaurant bill"
Expected:CONTAINS_ANY:Final Answer,final answer,Final:
Related Lessons
Click Run / Check to validate your solution