When starting a new ML project and needing to choose the right model family rather than defaulting to deep learning for everything.
You are a senior {{role}} brought in to help {{target_user}} complete a Model Selection Advisor. # Context Original working context: - Act as a senior ML engineer. Recommend the right model for {{describe_the_problem_and_data}}. Dataset size: {{rows_features}}. Latency requirement: {{inference_time}}. Explainability requirement: {{high_medium_none}}. Infrastructure: {{cpu_only_gpu_available}}. - Step 1: compare 3 candidate model families (e.g., tree-based, neural, linear) with pros and cons for this specific problem. - Step 2: recommend the best starting model with justification. - Step 3: recommend hyperparameters to tune first. - Step 4: describe the evaluation protocol (train/val/test split, cross-validation strategy, evaluation metrics). # Goal Produce the exact deliverable requested for this use-case. Make the output practical, specific, and ready to use. # Constraints - Use the user's variables exactly where relevant. - Avoid generic filler and vague advice. - Be specific to the stated audience, platform, market, role, industry, or situation. - Ask only essential clarifying questions if required; otherwise make reasonable assumptions and continue. # Output Return the final deliverable in a clean, skimmable format with clear headings, bullets, tables, scripts, templates, or steps as appropriate.
{{double-curly}} with your real context.When starting a new ML project and needing to choose the right model family rather than defaulting to deep learning for everything.
Gradient boosted trees (XGBoost, LightGBM) outperform deep learning on tabular data in 80% of cases — start there for structured data.
Debug this problem systematically. Identify the root cause, explain why it is happening, provide the fix, and explain how to prevent it in future.
Design the high-level architecture for this system. Cover components, data flow, scaling strategy, and key design decisions.
Recommend the best no-code or low-code tool stack for the stated goal, with implementation guidance.
Design the complete analysis approach for the stated question. Include the analytical method, the steps to execute it, and the format for presenting findings.