Robert Ta demos a Codex plugin that watches you work across apps, records what you do, and turns it into an AI skill you can reuse. He creates content in Meta's Cloud Code, switches to Obsidian to find career claims from his Workday days, and the system transcribes his narration and builds a prompt that actually grounds itself in real examples instead of making things up.
So this is a demo for AI builders on using the new plugin for Codex on how can you record your workflow manually on your computer and Codex will codify it as a skill. Any manual process, browser work, desktop work. So I'm going to go ahead and just start the recording here. So what I'm going to try to automate is in Cloud Code here, what I normally do is I'll create a bunch of threads, the platform by Meta for content. That's part of my top of funnel go-to-market strategy. Content strategy. What I then do is I go here and I go to Obsidian and I'll look at the threads. I'm like looking for areas where I'm most concerned about is where it talks about my previous employment. When I was lead product architect at Workday, we evaluated vendor reliability before deep integration. Simple question, will this company still support this product? So I'll go to here and I'll say, I evaluated threads.
Here are examples of good, bad usage of my career.
Cool. So what it's gonna do now is go and evaluate all of the ones around this particular criteria and then regenerate this. Let's go to Codex and stop.
Cool. I really like that you also, uh, narrated it and I'm curious if it's gonna pick up on that and include your narration within the skill prompt that it creates. Yeah, I'm really curious about that as well.
Find review note in Obsidian, locate examples of career context claims, copy good and bad examples, then feed them into our terminal. —codex prompt to calibrate against factual grounding versus hallucination. I'm checking the skill creation utilities next so the result is discoverable, not just a note. It seems like it did capture the audio context. I'm quite impressed. So they must have a really good transcription evals that performs really well within even just a normal conversation turn. For this kind of flow, I would have imagined as a user it would have taken me much longer if they're doing all of this synthesis of context on the backend to then fulfill the query.
Really impressive how deeply integrated it is with the operating system. And, you know, like their chronicling feature, you can see this too. They have a metadata event timeline of everything you're doing in the system. It's actually not intuitive to conceptualize what the system— what Codex has access to directly, you know, because it seems like it has system logs, it has metadata, it has screen share capability.
Yeah, this, for a one-shot, like, pretty damn good.
