This lesson contrasts three levels of AI memory: thin account-wide facts, more specific but AI-curated project memory, and a user-controlled system of plain-text files that an AI reads and maintains. It explains how scoped routing and explicit wrap-up updates preserve project context without contaminating unrelated work.
Jeff Su15 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 Jeff Su; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to design an AI memory system that scopes context by project while keeping every stored fact, rule, and update visible and editable by the user.
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.
2,738 cleaned transcript words reviewed across 824 timed caption segments.
Thesis
My AI Remembers Everything teaches a practical coding-agent workflow move: This lesson contrasts three levels of AI memory: thin account-wide facts, more specific but AI-curated project memory, and a user-controlled system of plain-text files that an AI reads and maintains. It explains how scoped routing and explicit wrap-up updates preserve project context without contaminating unrelated work.
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.
1:23
Global stays thin
“learnings from the day before. And you can confirm this yourself by opening up your AI's auto-generated memory. In ChatGPT, for example, this lives under personalization, the memory section, manage, where you'll probably notice that it's saved very...”
Account-level memory follows the user into every future chat, so chatbots deliberately preserve only broad facts such as role and writing preferences. Saving detailed context from every role or project at this level would inject irrelevant or incorrect information into unrelated conversations. Sort ten facts about your work and life into two lists: facts useful in nearly every chat and facts that belong only to a particular project.
8:08
Control the author
“ship what I call AI systems. For example, Anthropic has Claude co-work and Claude code. OpenAI has ChatGPT work and ChatGPT Codex. By the way, let me know if you want a video on ChatGPT work. And Gemini...”
Project memory creates a tighter boundary and can retain more work-specific detail, but the AI still decides what to save, where to put it, and when to update it. That means important facts such as confirmed attendees or a revised date can be omitted or become stale unless the human notices and corrects them. Inspect one ongoing project's remembered context and identify a fact the AI might omit, an entry that could become outdated, and who is responsible for correcting each one.
9:10
Route before loading
“task. Global context still cascades down, but now I decide where every memory write belongs, and the AI does the grunt work for me. So, let's see this in action. Here in Claude co-work, I have my Jeff...”
A level-three system begins each task by loading a small root memory file that routes the request to the owning project folder. The AI then reads that folder's latest memory and relevant material, so even a workspace with many active projects loads only the context needed for the current task. Create a miniature root memory file that maps three project names to separate folders, then list the project-specific files each route should load.
01
Inspect context
Start with this video's job: This lesson contrasts three levels of AI memory: thin account-wide facts, more specific but AI-curated project memory, and a user-controlled system of plain-text files that an AI reads and maintains. It explains how scoped routing and explicit wrap-up updates preserve project context without contaminating unrelated work. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 1:23, where the video says: “learnings from the day before. And you can confirm this yourself by opening up your AI's auto-generated memory. In ChatGPT, for example, this lives under personalization, the memory section, manage, where you'll probably notice that it's saved very...”
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 8:08, where the video says: “ship what I call AI systems. For example, Anthropic has Claude co-work and Claude code. OpenAI has ChatGPT work and ChatGPT Codex. By the way, let me know if you want a video on ChatGPT work. And Gemini...”
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: This lesson contrasts three levels of AI memory: thin account-wide facts, more specific but AI-curated project memory, and a user-controlled system of plain-text files that an AI reads and maintains. It explains how scoped routing and explicit wrap-up updates preserve project context without contaminating unrelated work.
02
Explain the practical stakes without hype: New playlist item from Jeff Su; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Brief -> Source material -> Generation -> Selection -> Edit -> Taste review -> Reusable recipe sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A creative production board with source inputs, prompt recipe, selection criteria, edit pass, and taste-review checkpoints.
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 AI Remembers Everything
- URL: https://www.youtube.com/watch?v=cEEw1AbeysI
- Topic: Creative Automation
- My current learning frame: Build a three-project plain-text memory prototype with one root routing file, one status file per project, and a wrap-up rule that records progress while flagging proposed permanent rules for approval.
- Why this matters: New playlist item from Jeff Su; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 1:23 / Evidence 1: "learnings from the day before. And you can confirm this yourself by opening up your AI's auto-generated memory. In ChatGPT, for example, this lives under personalization, the memory section, manage, where you'll probably notice that it's saved very..."
- 3:22 / Evidence 2: "context." And this can also give the AI information it needs. But this is also problematic because what if you didn't have a meeting about this presentation, and connectors also don't know what happened in a previous working..."
- 5:36 / Evidence 3: "any chat inside a project gets both the account level memory and the more specific project level context. For example, here I'm inside a Claude project, and although I can go in and view the project level memory,..."
- 8:08 / Evidence 4: "ship what I call AI systems. For example, Anthropic has Claude co-work and Claude code. OpenAI has ChatGPT work and ChatGPT Codex. By the way, let me know if you want a video on ChatGPT work. And Gemini..."
- 9:10 / Evidence 5: "task. Global context still cascades down, but now I decide where every memory write belongs, and the AI does the grunt work for me. So, let's see this in action. Here in Claude co-work, I have my Jeff..."
- 10:50 / Evidence 6: "in 1 week. Link down below. Back in the same Co-work session, let's continue working on the slide deck. Let's do the headline pass. Go through the deck and sharpen every slide headline so it states the inside."
- 13:01 / Evidence 7: "works across your entire workspace, not just inside one project. For example, if I say something like, "Draft an email updating my manager on the micro iPhone presentation," it routes to the folder holding my writing rules and..."
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 "My AI Remembers Everything", 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 global AI memory retain broad preferences but usually omit detailed project history?
What root problem do global memory and project memory share?
How does the level-three system find the right context without loading every active project?
Source shelf
Use the video as a doorway, then verify with primary sources.
