How to Verify AI Search Results Programmatically

import re

def extract_claims(text: str) -> list:
    """Extract verifiable claims from AI-generated text."""
    claims = []
    sentences = re.split(r'[.!?]\s+', text)
    for sentence in sentences:
        sentence = sentence.strip()
        if not sentence or len(sentence) < 20:
            continue
        # Claims with numbers/dates are verifiable
        has_number = bool(re.search(r'\d+', sentence))
        # Claims with proper nouns
        has_proper = bool(re.search(r'[A-Z][a-z]+(?:\s[A-Z][a-z]+)*', sentence))
        # Claims with comparison words
        has_comparison = any(w in sentence.lower() for w in
            ['fastest', 'largest', 'best', 'most', 'first', 'only', 'latest'])
        if has_number or has_comparison:
            claims.append({'text': sentence, 'type': 'numeric' if has_number else 'comparative'})
        elif has_proper:
            claims.append({'text': sentence, 'type': 'factual'})
    return claims

# Example AI answer to verify
ai_answer = """Python 3.14 was released in October 2025 with a new JIT compiler.
It is 2x faster than Python 3.12 for numeric workloads.
Guido van Rossum announced the change at PyCon 2025."""

claims = extract_claims(ai_answer)
for c in claims:
    print(f'  [{c["type"]}] {c["text"]}')

import requests, os

SCAVIO_KEY = os.environ['SCAVIO_API_KEY']

def verify_claim(claim: str) -> dict:
    # Build a verification query from the claim
    query = claim[:100]  # truncate long claims
    resp = requests.post('https://api.scavio.dev/api/v1/search',
        headers={'x-api-key': SCAVIO_KEY, 'Content-Type': 'application/json'},
        json={'query': query, 'country_code': 'us', 'num_results': 5})
    results = resp.json().get('organic_results', [])
    if not results:
        return {'claim': claim, 'status': 'unverified', 'confidence': 0, 'sources': []}
    # Check if results support the claim
    claim_lower = claim.lower()
    claim_keywords = set(re.findall(r'\b\w{4,}\b', claim_lower))
    support_count = 0
    sources = []
    for r in results:
        text = (r.get('title', '') + ' ' + r.get('snippet', '')).lower()
        result_words = set(re.findall(r'\b\w{4,}\b', text))
        overlap = len(claim_keywords & result_words) / max(len(claim_keywords), 1)
        if overlap > 0.3:
            support_count += 1
            sources.append({'title': r['title'][:50], 'url': r['link']})
    confidence = min(support_count / 3 * 100, 100)
    status = 'verified' if confidence >= 50 else 'disputed' if confidence >= 20 else 'unverified'
    return {'claim': claim[:60], 'status': status,
            'confidence': round(confidence), 'sources': sources[:2]}

import time

def verify_answer(ai_text: str) -> dict:
    claims = extract_claims(ai_text)
    if not claims:
        return {'trust_score': 0, 'claims': [], 'note': 'No verifiable claims found'}
    verified_claims = []
    for claim in claims:
        result = verify_claim(claim['text'])
        result['type'] = claim['type']
        verified_claims.append(result)
        time.sleep(0.3)
    # Compute trust score
    verified = len([c for c in verified_claims if c['status'] == 'verified'])
    disputed = len([c for c in verified_claims if c['status'] == 'disputed'])
    total = len(verified_claims)
    trust_score = round(verified / total * 100) if total > 0 else 0
    cost = total * 0.005
    print(f'Trust Score: {trust_score}/100')
    print(f'Claims: {total} total, {verified} verified, {disputed} disputed')
    print(f'Verification cost: ${cost:.3f}\n')
    for c in verified_claims:
        icon = 'PASS' if c['status'] == 'verified' else 'WARN' if c['status'] == 'disputed' else 'FAIL'
        print(f'  [{icon}] {c["claim"]}')
        if c['sources']:
            print(f'         Source: {c["sources"][0]["title"]}')
    return {'trust_score': trust_score, 'claims': verified_claims, 'cost': cost}

result = verify_answer(ai_answer)