$ cat /etc/cookies.conf
We use cookies to understand how people use this site.
Analytics cookies help us improve your experience.
They are off by default. Nothing tracks you until you say so.
$ select cookie_preferences
Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Demonstrating a OneNote search assistant that uses Microsoft Graph API, parallel processing, custom relevance scoring, caching, and token‑aware truncation for fast, accurate AI‑driven Q&A.
I plan to demo an AI-powered knowledge assistant that lets you query all of your OneNote content in natural language. It integrates Microsoft Graph API for data ingestion, uses parallel section processing and auto-escalation logic for fast/complete retrieval, and applies a custom relevance scoring system before passing context to OpenAI GPT models. Features like caching, token-aware truncation, usage tracking, and a responsive UI improves query latency.
Privacy-centric AI assistant uses local search and cost-capped GPT fallbacks.
Loading recent emails...