Previous Case Study • AI / Productivity
InboxFM
AI-native email assistant designed for priority-driven workflows.
Case IFRead full study →
Back to projects
AI / Documentation
Doxify
Outdated-page scanner and automated team QA assistant.
91.2%
Query Accuracy
1,240+
Stale Docs Flagged
-40%
Developer DMs
doxify.velnix.studio
Wiki Monitor Logs1 outdated file flagged
Scanning changes: repository velnix-studio/web...
Stale check: database_setup.md is out of sync with setup.sh (Modified 12 days ago)
bot
Slack Agent QA Response:"According to the database_setup.md document, PostgreSQL local port is mapped to 5432, but on the main branch the Docker Compose file now maps it to 5439. Run docker compose up -d to bind."
Overview
Doxify monitors your engineering wikis and Slack threads. By indexing code changes and detecting when document files fall out of sync with production code, it prevents document decay and automatically answers developer questions.
The Stack
Next.jsPythonLangChainPinecone Vector DBSlack Bolt SDKPostgreSQL
What We Shipped
Wiki monitor webhooks & change parser
LangChain RAG vector lookup module
Slack Bolt SDK conversational chatbot
Stale document reporting dashboard
The Challenge
Documentation starts clean but decays as code changes. Developers stop trusting search results and resort to asking colleagues in chat, repeating questions and distracting team members.
Our Solution
We engineered a wiki parser that monitors Git repository updates, runs difference scoring to identify stale documents, and handles vector search queries from a Discord/Slack bot to resolve questions automatically.
Keep Exploring
Other Case Studies
Next Case Study • Fintech / Developer tools
FakePE
API sandbox enabling developers to test edge-case payment flows.
Case FPRead full study →