The prompt that classifies 500 images without training a model

The Problem

In a document-processing project, I needed to classify images into architectural plans vs. site photos.

The traditional approach takes weeks: collect 5000+ labeled images, train a CNN (ResNet, EfficientNet), validate, tune hyperparameters, deploy endpoint, monitor drift.

The Approach

Instead of starting with dataset creation and CNN training, I used a different pattern:

• Define the classification rule clearly in the system prompt
• Send the image directly to the model
• Enforce a typed output schema
• Parse the result as structured data, not free text

That changed the entire delivery timeline.

from pydantic import BaseModel

class PhotoPlanResponse(BaseModel):
    is_plan: bool
    description: str

# Structured prompting + schema-enforced output
# No manual reading, no regex over prose
# No "maybe this means yes"
# No ambiguity for downstream systems

When This Works

Key Takeaway