DeepSerp / DeepAudit
An AI SEO/GEO optimization platform that improves how websites show up in ChatGPT, Perplexity, Gemini and Google AI Overviews.
- Python
- Django
- PostgreSQL
- Redis
- MongoDB
- ChromaDB
- OpenAI API
- LangChain
- RAG
What I built
A platform that crawls any public website, converts its content into structured data, audits it for AI search visibility, and recommends fixes. I built the universal scraping layer, the core AI modules and the backend that scores and tracks content in real time.
Modules
- DeepAudit: technical SEO and GEO audits that analyze metadata, schema, semantic HTML and data objects.
- PromptFlow: clusters prompts with vector embeddings to connect a site’s content to the questions users ask.
- CiteRank: tracks mentions, visibility and citations across AI engines in real time, and shows where the gaps are.
How it works
- A universal scraping system extracts content from any website stack: WordPress, React, Vue or Angular.
- A RAG-based recommendation engine built on OpenAI embeddings returns deploy-ready code fixes.
- The backend runs on Django, PostgreSQL, Redis and ChromaDB for real-time content scoring and tracking.
- An analytics dashboard shows AI readability scores, prompt clusters and performance heatmaps.