Implementation

# AI Coding Implementation Prompt Template

Use this template to structure your implementation requests to AI coding assistants. Fill in each section thoughtfully to ensure your prompt aligns with best practices and passes quality assessment.

---

## 1. Domain Context & Current Understanding

**What I know about this problem:**
- [Describe your current understanding of the domain/problem]
- [List relevant libraries, tools, or standards you're aware of]
- [Reference any existing implementations or approaches you've researched]

**What I'm uncertain about:**
- [Identify specific knowledge gaps]
- [List areas where you need guidance on best practices]

**Data characteristics:**
- Input types/shapes: [e.g., "pandas DataFrame with columns X, Y, Z; ~10K rows"]
- Expected output: [e.g., "dictionary mapping IDs to normalized scores"]
- Edge cases: [e.g., "missing values in column Y, duplicate IDs possible"]
- Constraints: [e.g., "must handle datasets up to 1M rows; memory < 2GB"]

---

## 2. Problem Statement (High-Level)

**What needs to be solved (not how):**

[Describe the problem conceptually, independent of implementation details. What are you trying to accomplish algorithmically?]

**Key steps in the solution approach:**
1. [Step 1 - conceptual]
2. [Step 2 - conceptual]
3. [Step 3 - conceptual]

**Architectural decisions:**
- Data structures: [e.g., "use hash map for O(1) lookups"]
- Algorithms: [e.g., "streaming processing to handle large files"]
- Design patterns: [e.g., "factory pattern for different data source types"]

---

## 3. Solution Plan & Requirements

**Inputs:**
- Parameter 1: [type, constraints, example value]
- Parameter 2: [type, constraints, example value]

**Outputs:**
- [Describe expected output format, structure, and validation criteria]

**Success criteria:**
- [What does successful execution look like?]
- [Performance requirements: speed, memory, accuracy]

**Integration context:**
- Existing codebase: [e.g., "fits into module X, uses interface Y"]
- Dependencies: [list libraries/versions, e.g., "pandas>=2.0, numpy>=1.24"]
- Interfaces to maintain: [e.g., "must accept same signature as existing function Z"]

---

## 4. Test Specifications

**Required test cases:**
1. **Happy path:** [Describe expected normal operation with sample input/output]
2. **Edge case 1:** [e.g., "empty input" - expected behavior]
3. **Edge case 2:** [e.g., "extremely large values" - expected behavior]
4. **Error condition:** [e.g., "invalid type" - should raise TypeError with message X]

**Acceptance criteria (as assertions):**