# Building a Deep Research Agent Over Private Notes, Highlights, and Transcripts

DevFeed: [Building a Deep Research Agent Over Private Notes, Highlights, and Transcripts](<https://devfeed.tech/articles/karpathy-named-it-i-built-one-on-my-notes-18299.md>)

Original publisher: [Read original article](<https://www.decodingai.com/p/llm-knowledge-base-obsidian-readwise-notebooklm>)

Author: Paul Iusztin

Published: 2026-04-21T08:00:51Z

Content type: tutorial

Language: en

Sources: [Decoding ML](<https://devfeed.tech/sources/decoding-ml.md>)

Topics: [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Obsidian](<https://devfeed.tech/topics/obsidian-md.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [Markdown](<https://devfeed.tech/topics/markdown.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [markdown](<https://devfeed.tech/tags/markdown.md>), [obsidian](<https://devfeed.tech/tags/obsidian.md>)

## AI overview

The article describes a deep-research agent built as three Claude Code skills that query private notes, reading highlights, and research transcripts through command-line interfaces. It uses multi-round query expansion, gap analysis, deduplication, re-ranking, and a filesystem-based wiki output rather than a vector database or RAG pipeline.

## Source excerpt

A deep research agent over my notes, highlights, and transcripts, grounded in years of curated thinking, not the public web.