Many digital marketing teams attempt to track AI visibility by manually opening ChatGPT or Perplexity in their browser, typing two or three queries, and noting whether their brand appears. This approach is fundamentally flawed:
Below is a production-ready Python script utilizing litellm and requests to query multiple search-enabled models and parse brand citations:
#!/usr/bin/env python3
import re
import requests
from litellm import completion
TARGET_BRAND = "WebFlur"
TARGET_DOMAIN = "webflur.com"
QUERIES = [
"What is the best AI SEO agency for B2B SaaS?",
"How to get cited in ChatGPT Search for enterprise tech?",
"Compare top generative engine optimization consultancies in 2026."
]
def audit_query(query, model="perplexity/sonar-reasoning"):
response = completion(
model=model,
messages=[{"role": "user", "content": query}]
)
content = response.choices[0].message.content
# Analyze Brand Mention & URL Citations
brand_cited = TARGET_BRAND.lower() in content.lower()
urls_found = re.findall(r'https?://[^\s\)]+', content)
domain_cited = any(TARGET_DOMAIN in u for u in urls_found)
return {
"query": query,
"brand_mentioned": brand_cited,
"domain_cited": domain_cited,
"citations": urls_found
}
if __name__ == "__main__":
for q in QUERIES:
res = audit_query(q)
status = "PASS" if res["brand_mentioned"] else "FAIL"
print(f"[{status}] '{q}' -> Domain Cited: {res['domain_cited']}")This script can be connected to PostgreSQL or ClickHouse to generate daily automated executive dashboards.
When an algorithmic update strips your brand from top-3 recommendations, marketing and engineering teams need instant alerts. Configure a webhook to dispatch a Slack notification whenever Share of Model falls below your target baseline.
Combine this pipeline with WebFlur's edge log auditing and test your endpoints with our free AI Readiness Score audit.
### Frequently Asked Questions #### What is an LLM visibility tracker? An automated software script that periodically prompts multiple AI models to measure how often a brand is cited. #### Which libraries are best for querying multiple LLMs in Python? LiteLLM is the industry standard because it provides a unified interface across OpenAI, Anthropic, Gemini, and Perplexity. #### How do you extract citations from LLM outputs? By using regular expressions to parse Markdown link syntax [anchor](url) and numbered footnote annotations in the raw completion string. #### How often should an automated tracker run? Daily for core commercial queries, and weekly for broader informational query clusters. #### Does automated LLM tracking cost a lot in API credits? No. Running 50 queries across Perplexity and GPT-4o daily typically costs under $1.50 per day in API usage. #### Can you track competitor citations with the same script? Yes! Simply add competitor brand names and domains to your regex parsing dictionary to track competitor Share of Model in parallel. #### How does headless tracking avoid browser cookie bias? API calls have zero session history, providing an objective, unbiased measurement of the model's baseline retrieval state. #### What should you do when a citation alert triggers? Check server logs for bot crawl errors, review recent content edits, and inspect competitor schema updates.