Jake Was Right: The Vault Started Producing Its Own Solutions

Many years as a mainframe administrator of an Application called ViewDirect, flat files, pointer indexes, report layouts. Started Cliff's Notes course a couple of months back. When he talked about structure over tools, it clicked immediately. I was heading down in our project and busted up my back and my elbow, so I was kind of immobilised for the last couple of weeks. I watched a half dozen of Jake's videos and was really excited. I started building it out like I was building that report warehouse again. Not the right way. Now that I've gone back and read some of the course, it's a start.

Here's a quick 12-minute (the Creative side background in tech, but what came out of it) fly-through of my vault operating as generative infrastructure. This view just showed that I'm very happy to be in the group. I really brought my mainframe experience up to date with the current technology. I felt I was lagging a month ago, two months ago, even after investing a pretty couple of years into it.

The vault isn't just storage; the agents kind of came out of it, building it (Merlin & Sarah from building the vault). Stock Obsidian. No plugins. Just folders and markdown, working like flat files always did.

Last, this weekend I should say, a friend and I created a quick story in an hour. We have other AI rapper programs from other groups that we use. They have a lot of genre outlines in them, just for brainstorming a story, and we sat down and did this.

Then, after my friend left, added the creative content to the Vault.

What happen for me was an incredible workflow. Something I'd been wanting to do for a couple of years emerged from the Vault, and here's what it is. I left a little bit at the end of this. You can just quit after a couple of minutes to see it evolve, but I left the creative process that came out this weekend in the video in there just as an example.

Current constraints for me are that I see why we need a vault and what they can do. The limiting aspect seems to be the input. This is the same as we had in the old days of mainframes. You have to be able to manage your queues. I just wanted to simply update files and move things around quickly.

The vault is functional, and it's producing things for me now. Just like Jake said, things came out of the vault. Even though it was organised by pointers and JSON files, I was able to build something, but I know that if I apply the folder system, it's going to be better.

The biggest constraint for me is that I could automate that to a certain degree, but I'm trying not to use plugins. We're back to the job-to-do kind of thing. I think Jake says the job to do, and that's what I've got to start thinking in that game.

Right now it's working, and I like to see what emerges out of it, but that is input queues.

Q's are critical for separating tasks for particular agents to get the workflow done.

For instance, if you watch my video and see how I spun up the storyboard at the end. It's not important from the tech side, more creative, but I would have to break that down step by step, and an input queue would need to handle each step so the models can do it efficiently. So Job-to-Folder?

A Marine once told me there are only two rules:

Read the manual.
When everything fails, go back to rule number one.

I'll go back to the modules. :)

There have been many developments that can address that problem. (Sorry guys, I got a parsing problem from one file. That's a later post. ) That's one that will develop and emerge from work like this group is doing.

I have a capture file everything goes into, but I have to parse them. It's in the video. I have to parse them into the report files. I didn't figure it out. YET.

I know many of you have already developed this. I'm looking at it because I'm coming from the creative side with a systems background, but anyway, that's one of the constraints I'm dealing with.

See less

12:53

1 comment

Jake Was Right: The Vault Started Producing Its Own Solutions