Anthropic Just Dropped Claude Memory 2.0 (Full Breakdown)
This video explains Claude's shared memory across Chat and cloud-run Co-work, including topic-by-topic memory capture, user editing and deletion, sensitive-topic controls, and importing memory from other AI providers. It demonstrates the central caveat that shared memory does not apply to locally run Co-work tasks or Claude Code.
Brock Mesarich | AI for Non Techies10 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 Brock Mesarich | AI for Non Techies; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to inspect, curate, and safely use Claude's shared memory across Chat and cloud-run Co-work while recognizing where that memory is unavailable.
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.
2,325 cleaned transcript words reviewed across 638 timed caption segments.
Thesis
Anthropic Just Dropped Claude Memory 2.0 (Full Breakdown) teaches a practical coding-agent workflow move: This video explains Claude's shared memory across Chat and cloud-run Co-work, including topic-by-topic memory capture, user editing and deletion, sensitive-topic controls, and importing memory from other AI providers. It demonstrates the central caveat that shared memory does not apply to locally run Co-work tasks or Claude Code.
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.
1:14
One Shared Memory
“is one of the reasons why a lot of people were only using Claude chat mode instead of co-work because we didn't have this persistent memory on us in our previous conversations. Now it says you can see...”
Claude Chat and Co-work now use the same persistent memory, so context learned in one can be available in the other without repeated explanations. Claude adds topic memories during a conversation rather than only summarizing at the end, while sensitive subjects such as health or beliefs are excluded by default unless the user enables them. List three non-sensitive facts that would reduce repeated setup in both Chat and Co-work, then decide whether any sensitive-topic memory should remain disabled.
4:13
Inspect and Curate
“is asking, "What about claude co-work and claude code and vice versa?" As of right now, this is only syncing between co-work and chat mode. There is no way for us to have a shared memory between co-work...”
The Memory settings organize saved information into profile, preferences, people, and topic files that users can open, enrich through chat, edit, or delete. The interface also offers an import path for memories from providers such as ChatGPT or Gemini, but the demonstrated synchronization covers Chat and Co-work—not Claude Code. Open the Memory settings, review one topic for accuracy, and either add one useful detail or remove one item you do not want retained.
7:45
Cloud Mode Required
“turn on So, if we turn on this new memory system, this works inside of Cloud Co-work in chat mode, but only in the cloud. But if we're running Claude Co-work on our computer locally, then it's not...”
The shared memory is available when Co-work runs a task in the cloud, where it can continue even after the desktop app or computer closes. A Co-work task running locally on the computer does not receive the same shared memory, although cloud-run Co-work can still be given access to selected local folders. Before starting a Co-work task that depends on saved context, check the desktop-versus-cloud selector and choose cloud mode, then verify recall with one known preference.
01
Inspect context
Start with this video's job: This video explains Claude's shared memory across Chat and cloud-run Co-work, including topic-by-topic memory capture, user editing and deletion, sensitive-topic controls, and importing memory from other AI providers. It demonstrates the central caveat that shared memory does not apply to locally run Co-work tasks or Claude Code. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 1:14, where the video says: “is one of the reasons why a lot of people were only using Claude chat mode instead of co-work because we didn't have this persistent memory on us in our previous conversations. Now it says you can see...”
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 4:13, where the video says: “is asking, "What about claude co-work and claude code and vice versa?" As of right now, this is only syncing between co-work and chat mode. There is no way for us to have a shared memory between co-work...”
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 video explains Claude's shared memory across Chat and cloud-run Co-work, including topic-by-topic memory capture, user editing and deletion, sensitive-topic controls, and importing memory from other AI providers. It demonstrates the central caveat that shared memory does not apply to locally run Co-work tasks or Claude Code.
02
Explain the practical stakes without hype: New playlist item from Brock Mesarich | AI for Non Techies; 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: Anthropic Just Dropped Claude Memory 2.0 (Full Breakdown)
- URL: https://www.youtube.com/watch?v=Fys9ua-x0A0
- Topic: Creative Automation
- My current learning frame: Create or refine one harmless preference memory in Claude Chat, retrieve it from a cloud-run Co-work task, add a second detail in Co-work, and confirm that the update appears back in Chat.
- Why this matters: New playlist item from Brock Mesarich | AI for Non Techies; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 1:14 / Evidence 1: "is one of the reasons why a lot of people were only using Claude chat mode instead of co-work because we didn't have this persistent memory on us in our previous conversations. Now it says you can see..."
- 4:13 / Evidence 2: "is asking, "What about claude co-work and claude code and vice versa?" As of right now, this is only syncing between co-work and chat mode. There is no way for us to have a shared memory between co-work..."
- 6:02 / Evidence 3: "click import memory from other AI providers. So, if I want to import our memory from ChachevT or Gemini, for example, I can do that right here. Next up, it breaks these down by categories, which I find..."
- 7:45 / Evidence 4: "turn on So, if we turn on this new memory system, this works inside of Cloud Co-work in chat mode, but only in the cloud. But if we're running Claude Co-work on our computer locally, then it's not..."
- 9:24 / Evidence 5: "create and then see if it translates over into chat mode. All right, so as for my pants, I kind of like my pants slightly oversized these days. Can you save that to the memory as well? Here..."
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 "Anthropic Just Dropped Claude Memory 2.0 (Full Breakdown)", 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.
How does the new memory system share context between Claude Chat and Co-work?
What controls does the Memory interface give users over saved information?
When does Co-work have access to the shared Chat memory?
Source shelf
Use the video as a doorway, then verify with primary sources.
