is the orchestration based on folder structure/ICM better that creating a knowledge graph and a semantic layer to get the required context from the knowledge graph. Which will yield better results if we evaluate both. What are the pros and cons of each approach?

Hi All, this is little different than the normal community post, but I trust the folks who have made it here because you don’t want BS sales pitch but something that works, ie the fundamentals… So my question is related to SEO and web traffic and how AI is changing that (I have zero experience in this area btw). I see a few different approaches to this such as refining content or making pages more ‘custom’ for users. But I also see people talking about having information accessible for the models themselves so that search results are pulling into the chats that people are using to get results rather than actually scrolling google search results pages. And then the wild card in my opinion is how MCP and those visual components can be inserted into chat windows now, continuing the ‘customization’ for the user (my guess is that UI will become even more user specific much like the text results we get back from the models currently). Not sure if all of that makes sense or is as connected as I think it is or will be. So my question: what are yall seeing and where can I start to double down on knowledge, much like Jake is doing here in the community. Thanks!

For those running agents on a recurring schedule (daily/overnight), I'm tightening my own setup and curious how you handle two things: 1. Stale or wrong context — how do you stop a scheduled run from acting on yesterday's state or drifting from the current workspace? Cold start every time, a freshness check, something else? 2. Autonomy vs approval — how much do you let a scheduled agent actually do unattended versus leave as a draft for you to approve? Where's your line between "just do it" and "prepare it and wait for me"? Mine currently drafts everything and waits for a human yes, but I suspect I'm leaving easy wins on the table by not letting it act on the safe stuff. Where do you draw the line, and what burned you?