customer_support · workflow
ApertureDB builds a RAG chatbot on its own documentation to surface and close content gaps
ApertureDB's documentation was scattered across multiple tools and repositories with no semantic search, making it hard for users unfamiliar with the product's specific terminology to discover how to accomplish tasks.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Documentation crawl ingestion
A crawl of the marketing website and product documentation is loaded into ApertureDB as the vector store backing the RAG chain.
Tools used
ApertureDBLangChainRAGLLMDocusaurus
Outcome
The RAG chatbot handles 10–50 queries per week on its alpha release, helps users discover documentation semantically without knowing ApertureDB-specific terms, and surfaces documentation gaps that the team then fills.
What failed first
GitHub Pages documentation went out of sync with the codebase, and separate Python SDK documentation in a second repository made lookup inconvenient with nothing tying the two sources together.
Results
Time saved10-50 queries a week
Volumeimmensely more powerful than mere keyword search
Grounding & classification
Source type: technical build writeup
24 fields verified against source quotes.
chatbotknowledge searchragsummarizationknowledge basefailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareemployee productivitythroughput increasetechnical build writeupcustomer supportrag answering