Free Tool

Extraction Lab

Run a paired before/after experiment on any URL. See exactly how HTML structure affects LLM fact extraction — token cost, accuracy, and hallucination rate.

Large language models like GPT-4, Claude, and Gemini consume raw HTML when extracting facts from web pages. Bloated markup — inline styles, deeply nested divs, tracking scripts — inflates token counts and degrades extraction accuracy. The Extraction Lab quantifies this effect by comparing how an LLM processes your original page versus a structurally optimized twin with the same visible content but cleaner HTML.

The experiment is fully deterministic: no LLM API calls are made. Instead, we simulate extraction using token counting, structural analysis, and a fact-density heuristic to estimate accuracy, cost savings, and hallucination risk before and after optimization.

We fetch the page, create a structurally optimised twin, and compare extraction metrics side-by-side. Zero LLM API calls — fully deterministic.

Overview
Before / After
Fact Extraction
Remediation
Golden String

Methodology

🔴 Original
🟢 Optimized

Token Noise Sources (Original)

Extracted Facts Comparison

Original Extraction

FieldValueMatch

Optimized Extraction

FieldValueMatch

Remediation Steps

    Copyable Patch

    
            

    The Golden Semantic String is what an LLM actually reads: Title + Meta + H1 + H2s + first ~600 words of body content + JSON-LD entities. Everything else is noise.

    Original Golden String

    Optimized Golden String

    Want the Full Deep Audit?

    Run a comprehensive crawl with template-level analysis, historical tracking, and automated remediation snippets.

    Start Deep Audit →

    Read the Research

    Our whitepaper documents the full methodology, case studies, and statistical proof that HTML structure causally determines LLM extraction accuracy.

    Read the Whitepaper →