What this note helps with

Use this note to turn repeated L&D research into reusable context that compounds across projects instead of disappearing after each deliverable.

* Updated as of May 2026. AI tool connection paths change, so verify the current tool behavior before making this a team standard.

Download the setup guide

Give Claude Code a Memory

Set up Obsidian as persistent context and living documentation for Claude Code projects, with Mission Control, a MEMORY index, session handoffs, and reusable L&D project notes.

Download PDF Open setup guide
What this feels like in the work

This feels like remembering that we solved this once, but not remembering where the answer went. The research is somewhere in a doc, chat, bookmark, slide deck, or prompt thread.

The problem

Learning teams gather articles, SME notes, tool research, and examples across many projects. Without a system, that context disappears when the project closes.

The system move

Use a small personal knowledge system for durable notes, source links, reusable prompts, and project context. The point is not more notes. The point is a system that can be reused.

What to inspect

Look for research you have repeated three times because the previous version was buried in email, chat, or a forgotten document.

Use this when
  • You keep researching the same tools, frameworks, examples, or standards
  • Prompt quality depends on context scattered across chats, docs, and bookmarks
  • Project knowledge disappears when the deliverable is complete
Diagnostic questions
  • What research have you repeated more than twice?
  • Which notes would help future work if they had a clear summary and source?
  • What project context should be reusable instead of temporary?
What to watch for
  • Research links saved without a note about why they mattered
  • Prompt threads that contain useful thinking but no reusable summary
  • Project notes that disappear when the deliverable is finished
What this can look like
  • Prompt-first adoption The team collects prompts, but we still have not defined source standards, review gates, or accountable owners.
  • Private productivity gains One person moves faster, but the shared workflow, QA process, and review standard stay the same.
  • AI output without evidence Drafts look polished, but reviewers cannot tell which sources were used or what still needs human judgment.
What we can try first
  • Create a small map of recurring L&D research topics
  • Add source links, short summaries, and project context to important notes
  • Keep prompts and examples near the research that supports them
  • Decide which notes are safe for direct local-agent use, copied excerpts, cloud exports, or NotebookLM-style source sets
Small experiment

Create one note for a recurring research topic and give it three sections. What we know, sources we trust, and open questions.

Three ways we can respond
  • No technology Write the rules for one AI-supported workflow on paper: allowed tasks, not-allowed tasks, required source checks, review owner, and publish criteria.
  • Microsoft 365 or Google Workspace Create a shared Word, Google Doc, or SharePoint page with approved prompts, source checklists, review criteria, and before-after examples.
  • AI-assisted Use AI to draft first-pass outlines, SME questions, accessibility checks, and QA checklists, then require human review for facts, tone, risk, and final decisions.
Sources