Obsidian AI Second Brain that ACTUALLY Works! (Codex, Claude Code)
Eric Michaud walks through the Obsidian second-brain system he uses daily, split into three parts: a provider-agnostic local vault of markdown files with front-matter tags, a strict separation between a 'human' folder for verbatim ideas and a 'machine' side that AI agents (Codex, Claude Code) manage via an instructions file, and an intelligence layer built from daily notes that surfaces which actions actually drive results.
Eric Michaud14 minTranscript found
Quick learning frame
Read this before watching.
Coding-agent workflow is the loop of inspect, route, plan, edit, verify, summarize, and decide what should be automated next.
New playlist item from Eric Michaud; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to structure a personal knowledge vault so AI agents handle the data-entry friction without contaminating your own thinking, and to use daily-note correlations to separate being busy from being productive.
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.
01Inspect context
02Route tool
03Plan work
04Edit safely
05Verify behavior
06Report next step
Deep lesson
Turn this video into working knowledge.
3,492 cleaned transcript words reviewed across 966 timed caption segments.
Thesis
Obsidian AI Second Brain that ACTUALLY Works! (Codex, Claude Code) teaches a practical coding-agent workflow move: Eric Michaud walks through the Obsidian second-brain system he uses daily, split into three parts: a provider-agnostic local vault of markdown files with front-matter tags, a strict separation between a 'human' folder for verbatim ideas and a 'machine' side that AI agents (Codex, Claude Code) manage via an instructions file, and an intelligence layer built from daily notes that surfaces which actions actually drive results.
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.
1:12
Local, tagged, provider-agnostic
“you're the type of person that wants to grab the templates and just get out of here, that's okay, too. I'll make sure to leave the links to all the resources in the description there. There'll be some...”
Obsidian's appeal is that everything is plain local markdown you own — unlike Evernote-style lock-in — so the same vault plugs into Claude Desktop, Claude Code, Codex, or Hermes, while front-matter tags (e.g. email, inbox, spam, follow-up on a task note) make every note findable by tag or via the linked graph, not just by title. Add front-matter tags to five existing notes in your own system, then retrieve each one by tag instead of title to prove the linking works.
8:34
Instructions file runs the machine side
“have this instructions file at the root of whatever project they're working on, but they have different naming conventions. I, for example, use Codex most often, so they call it agents. That's OpenAI's way. If you're using Anthropic,...”
The AI half of the vault is governed by a root instructions file — AGENTS.md for Codex, CLAUDE.md for Anthropic, Gemini for Google — that loads every session with a map of the vault, the front-matter conventions, and where skills live (a workflows folder invoked via slash commands), so the agent follows the rules and writes outputs only to its own side. Draft an instructions file for one folder you would let an agent manage: describe the folder map, naming conventions, and an explicit rule about where outputs may be written.
9:48
Intelligence, not dashboards
“all of my skills. So, for example, if I was just starting this vault and I wanted to run the interview skill, I would go {slash} interview. Agent's already primed to look here for that skill. Other than...”
Part three is not habit-tracker flexing — it uses the front matter already accumulating in daily notes to expose correlations (how an activity affects revenue, mood, time with family) so you can identify the 20% of actions producing 80% of results and pick just three priorities per day. For one week, log two or three personal metrics in your daily notes, then ask an AI agent to chart how they move together and name one activity to cut.
01
Inspect context
Start with this video's job: Eric Michaud walks through the Obsidian second-brain system he uses daily, split into three parts: a provider-agnostic local vault of markdown files with front-matter tags, a strict separation between a 'human' folder for verbatim ideas and a 'machine' side that AI agents (Codex, Claude Code) manage via an instructions file, and an intelligence layer built from daily notes that surfaces which actions actually drive results. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 1:12, where the video says: “you're the type of person that wants to grab the templates and just get out of here, that's okay, too. I'll make sure to leave the links to all the resources in the description there. There'll be some...”
02
Route tool
Use "Route tool" to locate the part of the coding-agent workflow mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 8:34, where the video says: “have this instructions file at the root of whatever project they're working on, but they have different naming conventions. I, for example, use Codex most often, so they call it agents. That's OpenAI's way. If you're using Anthropic,...”
03
Plan work
Turn "Plan work" into the reusable artifact for this lesson: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal. This is where watching becomes something you can inspect and reuse.
04
Edit safely
Use "Edit safely" 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
Verify behavior
Use "Verify behavior" 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
Report next step
Use "Report next step" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed artifact packet
Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
Example
Coding-agent workflow proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the coding-agent workflow pattern.
Example
Teach-back module
Transform the lesson into a definition, a Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step 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.
choosing tools by hype
losing context across agents
letting parallel sessions become invisible
Letting the lesson drift into generic Codex vs Claude comparison.
Letting the lesson drift into feature lists without task routing.
Letting the lesson drift into claims that ignore limits or recovery.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: Eric Michaud walks through the Obsidian second-brain system he uses daily, split into three parts: a provider-agnostic local vault of markdown files with front-matter tags, a strict separation between a 'human' folder for verbatim ideas and a 'machine' side that AI agents (Codex, Claude Code) manage via an instructions file, and an intelligence layer built from daily notes that surfaces which actions actually drive results.
02
Explain the practical stakes without hype: New playlist item from Eric Michaud; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
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: Obsidian AI Second Brain that ACTUALLY Works! (Codex, Claude Code)
- URL: https://www.youtube.com/watch?v=slkO_QAkqlc
- Topic: Creative Automation
- My current learning frame: Build a starter vault with separate human and machine folders, write an agent instructions file mapping the structure, then test it by asking Codex or Claude Code to add a task to today's daily note and verify it lands in the right place with correct front matter.
- Why this matters: New playlist item from Eric Michaud; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 1:12 / Evidence 1: "you're the type of person that wants to grab the templates and just get out of here, that's okay, too. I'll make sure to leave the links to all the resources in the description there. There'll be some..."
- 4:22 / Evidence 2: "kind of removes it, right? All that input stuff, all this boring formatting, AI can just take care of for you. So, I chose to do it in my local terminal, but this is the cool part is..."
- 6:47 / Evidence 3: "working on a project, and then I'll have an idea pop into my head, and I just write it down and continue on, okay? Cuz because I the way I think of it, your brain only has so..."
- 8:34 / Evidence 4: "have this instructions file at the root of whatever project they're working on, but they have different naming conventions. I, for example, use Codex most often, so they call it agents. That's OpenAI's way. If you're using Anthropic,..."
- 9:48 / Evidence 5: "all of my skills. So, for example, if I was just starting this vault and I wanted to run the interview skill, I would go {slash} interview. Agent's already primed to look here for that skill. Other than..."
- 11:22 / Evidence 6: "things work together? So, that I can honestly look back on any day like through the daily log and see that like when I do this, this is how it affected my revenue. This is how it affected..."
- 13:52 / Evidence 7: "done properly rather than just like winging it like all of us have done for a little while now. Also, check out my school community. There's a lot of resources on how to build things out, but not..."
Video-aware target:
- Prompt lane: Coding-agent workflow
- Mechanism to extract: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review.
- Artifact to produce: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
- Artifact must include: task class; agent/tool choice; context packet; verification step; handoff/recovery rule
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, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step
- answers to these source questions: What workflow pain is being solved? | What exact coordination mechanism is shown? | What evidence proves it changes the work?
- 3 concrete examples that apply the video idea to real agentic work, such as rate-limit routing; browser verification after a UI edit; long-running /goal session review
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: choosing tools by hype; losing context across agents; letting parallel sessions become invisible
- a checklist for the next real workflow, focused on: routing decision, context portability, verification, handoff summary
- one practical exercise with a clear done signal: Route three recent tasks across Codex, Claude, browser checks, and manual review with a reason for each.
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 "Obsidian AI Second Brain that ACTUALLY Works! (Codex, Claude Code)", not a generic Creative Automation essay.
- Each workflow rule must point to a timestamped claim or demo moment, then state what remains unproven.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic Codex vs Claude comparison; feature lists without task routing; claims that ignore limits or recovery.
- If evidence is weak or missing, stop and 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.
Creative AI removes the need for taste.
It increases the need for taste because output volume explodes.
The best prompt is enough.
References, critique, iteration, and post-production matter just as much.
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 coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
A reusable artifact with a done signal and one verification step.03
Coding-agent workflow teach-back card
Explain the coding-agent workflow mechanism 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.
Why does the video argue Obsidian beats tools like Evernote or Notion as an AI-era second brain?
What role does the root instructions file (AGENTS.md / CLAUDE.md) play in the machine side of the vault?
What is the actual purpose of the intelligence layer, according to the video?
Source shelf
Use the video as a doorway, then verify with primary sources.
