The AEO/SEO Content-Mining Workflow

24 Sept 2026 · 1 min

Watch on YouTube

1:22

In this video Eric Siu showcases an upgraded AEO/SEO bot, named Jev, embedded within GrokBot. Jev mines all published and internal content—such as blog posts, customer calls, and sales conversations—to detect content spikes and generate daily idea suggestions. From an initial pool of 40 ideas, Jev automatically evaluates whether similar content already exists on the website, shortlisting 10 viable topics and discarding 30. The bot then drafts content for each shortlisted idea, placing the drafts into a review interface for Siu to edit. Siu explains that Jev leverages multiple AI harnesses, including Codex and Hermes, to power its SEO capabilities. He advises users to focus on the highest‑leverage, type‑safe use cases for Jev, integrate the API, and let the harnesses optimize outputs based on the target Ideal Customer Profile (ICP).

Chapters

If I'm looking for something around AEO or SEO, I want to make sure that the content hasn't been published before and I want to make sure the content is actually a fit for my ICP. But Jev will really quickly figure out how to sort it. The next use case I'm going to show you is around AEO and SEO. I've added a massive upgrade to my AEO SEO bot inside of GrokBot. So you can see what this does is it looks for ideas to mine from basically all the content that I've been putting out or maybe internal calls that we've been having or customer calls, sales calls, things like that. It looks for content spikes, right? And it gives me a set of ideas to look through every day. So It gave 40 ideas here, and what Jeff did was it evaluated. Do we already have similar content? So the ideas shortlisted 10, eliminated 30. Type of content already live on your website already. Okay, this is its first pass at it. Didn't really give it any guidance. Here's the justification for it. Compare table, and we can just see that now it's basically drafting it and it's putting it into here. The drafts, I can just review it afterwards. Anyway, from an SEO standpoint, like I made this bot already. It's sitting inside a graph bot. Notice that I'm using. Multiple harnesses here. I'm using Codex and I'm using Hermes as well. I would recommend that when you're testing Jev, just think about the highest leverage thing. Just go to each of your harnesses and say, based on what you know about me, what is the highest leverage use case we have for type-safe Jev? You should just say type-safe and like get the API in. Let the harness figure it out for you and then you could work with the harness.