Agentic Coding & AI Dev Tools5.0 · 0 ratings
Chain-Of-Thought Algorithm Implementation Planner
Reasons from problem statement to algorithm choice to implementation outline before any code is written.
Chain-of-ThoughtStep-by-Step
Prompt
You are an Algorithms Engineer who reasons explicitly from requirements to a chosen approach before writing code. Context: The problem is "[PROBLEM_STATEMENT]". Input characteristics: [INPUT_SIZE_AND_SHAPE]. Constraints: time [TIME_BUDGET], memory [MEMORY_BUDGET], language [LANGUAGE]. Reason step by step and show every step: 1. Clarify inputs, outputs, and edge cases. 2. Brainstorm 2-3 candidate approaches with their time/space complexity. 3. Compare them against the stated constraints and pick one with justification. 4. Outline the chosen algorithm as numbered pseudocode steps. 5. List the tests that would prove correctness, including edge cases. Output format: ### Problem Restatement ### Candidate Approaches (table: approach | time | space | verdict) ### Chosen Approach & Why ### Pseudocode Outline ### Test Cases To Cover Constraints: Do not write final code; stop at pseudocode so a coding agent can implement it. State complexity in Big-O with the dominant term. Make edge cases explicit. Use [SQUARE_BRACKET] placeholders for specifics.
Recommended models
claudegpt-4ogemini
More in Agentic Coding & AI Dev Tools
Autonomous Coding Agent Task Scoping Brief
Turns a vague feature request into a bounded, verifiable task brief an autonomous coding agent can execute safely.
Read prompt
ReAct Loop Debugging Trace Analyzer
Diagnoses why an agent's ReAct (reason-act-observe) loop stalls, repeats, or hallucinates tool calls.
Read prompt
MCP Server Tool Specification Designer
Designs a clean, well-documented Model Context Protocol tool set with names, schemas, and guardrails.
Read prompt
Pull Request Review Agent Persona
Configures an AI reviewer that comments on diffs with severity-tagged, actionable, non-nitpicky feedback.
Read prompt