Agent Architecture / Foundation

My Obsidian Vault in 2026 - What I Actually Open Every Day

A four-year Obsidian user walks through the workspace-driven vault he actually opens daily — using the Commander status bar plus a forked Workspace Plus plugin to jump between focus, active, RSS, discoveries, and cycles-and-reviews layouts — and shows how Quick Add, Notebook Navigator, and Bases replace older DataView/Templater habits for capturing and finding notes with minimal friction.

Paul's Obsidian SystemsWatchTranscript found

Quick learning frame

Read this before watching.

A model becomes useful when it is wrapped in a harness: tools, state, permissions, memory, routing, and verification.

New playlist item from Paul's Obsidian Systems; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Skill you build: The ability to design a workspace-switching Obsidian system that routes every kind of work (writing, capture, review, journaling) into a dedicated saved layout so you spend zero effort deciding where notes go or how to surface them.

Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.

Concept diagram

Where this video fits.

01Intent
02Model
03Harness
04Tools
05Verifier
06Artifact

Deep lesson

Turn this video into working knowledge.

4,640 cleaned transcript words reviewed across 1,247 timed caption segments.

Thesis

My Obsidian Vault in 2026 - What I Actually Open Every Day teaches a practical agent architecture move: A four-year Obsidian user walks through the workspace-driven vault he actually opens daily — using the Commander status bar plus a forked Workspace Plus plugin to jump between focus, active, RSS, discoveries, and cycles-and-reviews layouts — and shows how Quick Add, Notebook Navigator, and Bases replace older DataView/Templater habits for capturing and finding notes with minimal friction.

The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.

0:00

Workspace switching hub

“This is my Obsidian Vault. >> >> A while back I made a video about every Obsidian Vault I'd ever built. The question people kept asking me was the obvious one, what do you actually use now? So,...”

He drives the whole vault from a Commander status-bar button instead of menus: the core Workspaces plugin saves/loads layouts, but he prefers a forked Workspace Plus (the original had 74k downloads but died 3 years ago and was buggy) because it lists layouts sorted A–Z and he added a save icon himself. Enable the core Workspaces plugin, save your current layout, then install Commander and add the 'manage workspace layouts' and 'save layout' commands to your status bar so switching is one click.

8:25

Frictionless capture

“So, if I want to create a new note, I can select this one here. It prompts me for the note name, so I'll call this one quick add demo. And it's just going to load my template...”

A Quick Add status-bar command prompts for a note name, applies the right template with predefined YAML, drops it in the note lab, and opens it in a new tab — removing the 'which template, which folder' decision; he then re-finds notes via the quick switcher (Ctrl+O), Notebook Navigator, and the Recent Notes plugin. Set up one Quick Add 'new note' choice wired to a template and auto-open-in-new-tab, then create a test note and practice retrieving it three ways: quick switcher, Notebook Navigator, and Recent Notes.

17:13

Cycles and reviews

“daily there because it is actually on the calendar. So, what I do is I attend to select the calendar date here, then it grabs my New Delhi note, I hit create, and then it prompts me with...”

His journaling workspace ties a calendar (a dot under each day marks a daily journal) to daily/weekly/monthly/yearly notes; he clicks a date, the new daily note prompts three reflection questions (mind dump, today's focus, overall mood), and includes a habit tracker, with a separate Reflect chord command for reviewing entries. Build a daily-journal template with a calendar view and three fixed prompts (a mind dump, today's focus, your mood), then fill one out today and commit to anchoring it on the calendar each morning.

01

Intent

Start with this video's job: A four-year Obsidian user walks through the workspace-driven vault he actually opens daily — using the Commander status bar plus a forked Workspace Plus plugin to jump between focus, active, RSS, discoveries, and cycles-and-reviews layouts — and shows how Quick Add, Notebook Navigator, and Bases replace older DataView/Templater habits for capturing and finding notes with minimal friction. Treat "Intent" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:00, where the video says: “This is my Obsidian Vault. >> >> A while back I made a video about every Obsidian Vault I'd ever built. The question people kept asking me was the obvious one, what do you actually use now? So,...”

02

Model

Use "Model" to locate the part of the agent architecture workflow the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 8:25, where the video says: “So, if I want to create a new note, I can select this one here. It prompts me for the note name, so I'll call this one quick add demo. And it's just going to load my template...”

03

Harness

Turn "Harness" into the reusable artifact for this lesson: A one-page agent harness map with tool boundaries and proof signals. This is where watching becomes something you can inspect and reuse.

04

Tools

Use "Tools" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.

05

Verifier

Use "Verifier" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.

06

Artifact

Use "Artifact" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.

Example

Source-backed work packet

Convert the video into a scoped task that includes the transcript claim, target workflow, acceptance criteria, and proof. The output should be a one-page agent harness map with tool boundaries and proof signals..

Example

Claim vs. demo brief

Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the workflow.

Example

Teach-back module

Transform the lesson into a definition, a mechanism diagram, one misconception, one practice exercise, and a check-for-understanding question.

Do not learn it wrong
  • Treating the title as the lesson without checking what the transcript actually says.
  • Letting the prompt drift into generic advice that could apply to any video in the playlist.
  • Copying the tool setup without identifying the operating principle that transfers to your own stack.
  • Skipping the artifact, which means the learning never becomes operational or inspectable.

Transcript-derived moments

Use timestamps to study the actual video.

Quality check

Do not count this as learned until these are true.

01

State the transcript-backed claim in your own words: A four-year Obsidian user walks through the workspace-driven vault he actually opens daily — using the Commander status bar plus a forked Workspace Plus plugin to jump between focus, active, RSS, discoveries, and cycles-and-reviews layouts — and shows how Quick Add, Notebook Navigator, and Bases replace older DataView/Templater habits for capturing and finding notes with minimal friction.

02

Explain the practical stakes without hype: New playlist item from Paul's Obsidian Systems; queued for transcript-backed review, topic mapping, and a practical learning artifact.

03

Map the idea onto the Intent -> Model -> Harness -> Tools -> Verifier -> Artifact sequence and name the weakest link.

04

Produce the artifact and include the evidence that proves it: A one-page agent harness map with tool boundaries and proof signals.

Put it into practice

Give this grounded prompt to Codex or Claude after watching.

You are helping me turn one specific YouTube video into real, durable learning.

Source video:
- Title: My Obsidian Vault in 2026 - What I Actually Open Every Day
- URL: https://www.youtube.com/watch?v=nNvQMDbzdBg
- Topic: Agent Architecture
- My current learning frame: Pick the three kinds of work you do most (e.g. writing, capturing links, journaling), create and save a dedicated Obsidian workspace for each, wire them to a Commander status-bar switcher, and route new notes through a single Quick Add command so you can move between modes without ever deciding where a note belongs.
- Why this matters: New playlist item from Paul's Obsidian Systems; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:00 / Evidence 1: "This is my Obsidian Vault. >> >> A while back I made a video about every Obsidian Vault I'd ever built. The question people kept asking me was the obvious one, what do you actually use now? So,..."
- 5:53 / Evidence 2: "jump from RSS over to discoveries, and here I have my content discovery system. So, you can see that I've got Nate's video here. So, open up this one. So, this one is something I need to review."
- 8:25 / Evidence 3: "So, if I want to create a new note, I can select this one here. It prompts me for the note name, so I'll call this one quick add demo. And it's just going to load my template..."
- 11:12 / Evidence 4: "and then I have all my notes created for May, and I could either find it in my little local graph view here, or find it on the left-hand side, and you can sort by months here. So,..."
- 17:13 / Evidence 5: "daily there because it is actually on the calendar. So, what I do is I attend to select the calendar date here, then it grabs my New Delhi note, I hit create, and then it prompts me with..."
- 19:15 / Evidence 6: "monthly, quarterly reviews automatically with AI tools. So, I'm going to use a cloud command in order to do that. So, you will show you that in the next video. All right, let's flush out some more things..."
- 24:11 / Evidence 7: "my local graph view. And I can go explore those notes about mindset. So, having a nice foundation like this allows me to just explore through particular topics that I need to brush up on or explore further."

Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable claims from the video. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A one-page agent harness map with tool boundaries and proof signals.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Intent -> Model -> Harness -> Tools -> Verifier -> Artifact
   - 3 concrete examples that apply the video idea to real agentic work
   - 2 failure modes the video helps prevent
   - a checklist I can use the next time I run Codex or Claude
   - one practical exercise with a clear done signal
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.

Quality bar:
- Make this specific to "My Obsidian Vault in 2026 - What I Actually Open Every Day", not a generic Agent Architecture essay.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- If evidence is weak, say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.

Misconceptions

What to stop believing.

A better model automatically makes a better agent.

The model matters, but harness design determines whether the system can act safely and repeatably.

More tools always help.

Every tool increases surface area. Strong agents have the right tools with clear permissions.

Memory means saving everything.

Useful memory is compressed, curated, and tied to future decisions.

Practice studio

Learning only counts when you make something.

01

Transcript evidence map

Separate what the video actually says from what you already believe about the topic.

3 source-backed takeaways with timestamps, confidence, and a transfer note.
02

One useful artifact

Apply the video to a real workflow and produce a one-page agent harness map with tool boundaries and proof signals..

A reusable artifact with a done signal and one verification step.
03

Teach-back card

Explain the lesson to someone who has not watched the video yet.

A 90-second explanation, one diagram, one example, and one misconception to avoid.

Recall check

Answer first, then reveal — without rewatching.

Paul prefers a status-bar 'switch workspace' command over the core Workspaces plugin's manager for one concrete reason. What is that reason, and what is the catch with the plugin behind it?

What does Paul's Quick Add 'new note' command automate so he doesn't have to make decisions when capturing, and which three methods does he use to re-find a note afterward?

In Paul's Cycles and Reviews workspace, how does the calendar indicate a daily journal exists, and what three prompts does a new daily note ask him to fill in?

Source shelf

Use the video as a doorway, then verify with primary sources.

DocsOpenAI Agents SDK: agents

Read this for the basic object model: instructions, tools, handoffs, guardrails, and structured outputs.

openai.github.io/openai-agents-python/agents/
DocsOpenAI Agents SDK: tracing

Use this to understand why observability is part of agent architecture.

openai.github.io/openai-agents-python/tracing/
DocsOpenAI Agents SDK: guardrails

Good follow-up for thinking about boundaries, tripwires, and tool-level checks.

openai.github.io/openai-agents-python/guardrails/
DocsOpenAI Agents SDK: handoffs

Explains delegation between specialized agents and what context gets forwarded.

openai.github.io/openai-agents-python/handoffs/
ReadingModel Context Protocol

Useful for understanding how external tools and context servers become part of the agent environment.

modelcontextprotocol.io/introduction
PodcastLatent Space: The AI Engineer Podcast

Best ongoing podcast lane for agent tooling, AI engineering, codegen, infra, and model shifts.

www.latent.space/podcast
PodcastPractical AI podcast archive

Older but still useful practical conversations on agents, AI engineering, and production concerns.

changelog.com/practicalai/