[alexsmirnov]

I do use Obsidian on pair with Claude code and git.

I organize notes by tags, folders, and links from tree of "map of content" notes. Those documented as rules for AI. All notes came to "Inbox" folder, and from time to time I run special script that checks inbox, formats notes, tags them, and put in the most appropriate place. "git diff" to check results and fix mistakes, reset if it went wrong.

As notes organized by the limited number of well defined rules, they became easy to search and navigate by AI. Claude Code easily finds requested notes, working as advanced search engine, and they became a starting point for "deep research" : find relevant notes, follow links, detect gaps, search internet. Repeat until reach required confidence level.

The most advanced workflow so far is combination of TRIZ (Theory of Inventive Problem Solving) + First Principles Framework. Former generates ideas and hypotheses, later validates them and converge on final answer.

[item007]

This is a great example of making the system trustworthy: Inbox → scripted processing → git diff review → reset if needed. The diff-as-trust-layer feels like the missing piece for a lot of “AI organizes my notes” ideas.

Also +1 on “limited rules” being more important than fancy models — once the structure is predictable, Claude becomes a genuinely useful retrieval and research assistant.

Out of curiosity, where does the loop close for you today? After “deep research” produces a conclusion, do you write back into a MOC / decision log / project note, or does it mostly live in chat + commits? I’m exploring a similar loop (context → retrieval → suggestion → human review → write-back) with the same constraint: keep it auditable and reversible (diff-friendly). Details are in my HN profile/bio if you want to compare approaches.