Few-Shot Prompting: 36% Higher Accuracy

The Problem: Your AI Can't Read Technical Documents

You've tried GPT-4 Vision on your technical drawings. The results? Garbage.

Standard AI approaches fail on specialized documents because:

• No domain knowledge: The model doesn't understand switchboard layouts, tier structures, or component conventions
• No visual anchors: It can't distinguish what's important from what's noise
• Inconsistent outputs: Every response has a different format, breaking your downstream processing
• Missed sections: Critical data gets overlooked entirely

Our client faced exactly this. They needed to extract tier numbers, widths, ventilation status, and component values from electrical switchboard drawings.

First attempt with zero-shot prompting: 18.2% accuracy.

That's not a typo. The AI got it right less than 1 in 5 times.

What if you could triple that accuracy without changing models or increasing costs?

What We Built: Few-Shot + Computer Vision Pipeline

We combined two techniques that individually help, but together create something powerful:

The Results

The tier count went from 72.7% to 100%. The zero-shot model fundamentally misunderstood the document structure. With examples, it got it right every single time.

Step 1: Computer Vision Preprocessing

Before the LLM ever sees your document, prepare it visually.

We trained a lightweight detection model (Roboflow) to identify key components:

• MCMP plates: Yellow overlay + green border
• Metering units: Blue border outline

The LLM receives a "cheat sheet" image. Instead of scanning the entire complex drawing, it knows exactly where to focus.

Think of it like highlighting a textbook before an exam. The content is the same, but the important parts are marked.

Step 2: Few-Shot Examples That Actually Work

The difference between good and great few-shot prompting is example selection.

Bad Examples

• All similar complexity
• Same document type
• No edge cases

Good Examples (What We Used)

• Example 1: Simple layout, minimal components
• Example 2: Heavy ventilation, complex tier structure
• Example 3: Mixed components, unusual widths
• Example 4: Edge case with missing data

Key insight: 4 diverse examples beat 20 similar ones. Quality and coverage matter more than quantity.

Step 3: Enforce Structure with Pydantic

Even with great examples, LLMs can output malformed JSON. We use Pydantic to guarantee valid outputs — no more JSON parsing errors, no missing fields, no type mismatches.

What You Can Apply Today

1. Don't start with the LLM. Use CV to preprocess and highlight key regions first.
2. Build a diverse example set. Cover edge cases, not just happy paths. 4-6 high-quality examples beats 20 mediocre ones.
3. Enforce structure. Use Pydantic, Zod, or JSON Schema. Never trust free-form LLM output in production.
4. Measure properly. Track exact match rate AND field-level accuracy. They tell different stories.

Results Summary