Part 7 of the Building the AI Memory Stack series
Back in Part 1, I made a promise: memory eventually becomes voice.
Up to this point, we've built the architecture that makes trustworthy memory possible.
The Context Window executes work.
Active W...
I went looking for a better runtime check and found a different way to think about the problem.
I have spent a lot of time recently thinking about what an AI agent should be allowed to do.
Reading data is one thing. Writing durable state is another...
Part 6 of the Building the AI Memory Stack series
At the end of the last article, I left one question unanswered.
> Can you prove this record is exactly what was written?
Write-Side Custodyhttps://sovereignplatform.dev/terms/write-side-custody.htm...
Because "we'll be in touch" is not an observable state.
I submitted a job application recently.
It was one of those applications where you actually put in the effort. I read the job description carefully, tailored the resume, wrote a cover letter s...
Part 5 of the Building the AI Memory Stack series
The previous articles introduced the Reasoning Ledger and then worked through what a single ledger record should contain. Together they answered a hard question: why did this decision happen, and how...
Part 4 of the Building the AI Memory Stack series
After finishing the previous article, I looked at the repository a little differently. The specifications were still there. The Architecture Decision Records were still there. The glossary entries we...
What happens when a thousand independent sources turn out to have one parent?
A while back I went looking for a specific piece of television. A 2012 late-night interview with a sitting president, forty-five minutes long, broadcast on a major network...
Part 3 of the Building the AI Memory Stack series
After finishing Part 2, I noticed something.
The browser tabs I had open while writing it were gone. The temporary notes were gone. The diagrams existed only while I was drafting.
The article remai...
Agentic Memory and the Digital Passport
In moving into the workshop, we’re working on a Material-CV tool which performs geometric audits. We know we have 280 staves and exactly enough wide material for four side tables. But in the Salvaged Barrel S...
Part 2 of the Building the AI Memory Stack series
When I published the first article in this series, I thought I was writing about context windows.
The more I wrote, the more I found myself bouncing between documents. I had the glossary open in one...
One of the most common misconceptions in modern AI is that a larger context window somehow "solves" memory.
It doesn't.
A context window increases how much information a model can consider during a single inference. It does not give the system a du...
Provenance, Logistics, and the Unbroken Chain
Our last post on a Pivot Engine identified a 96 hour window to move 20 tons of Riesling into the culinary market. The decision is made and the tractors are out. But as soon as those grapes leave your gat...
In July of 1776, an experimental political concept was ratified on the extreme edge of the known geopolitical world. It was a declaration that governance belongs at the local perimeter, that centralized authorities separated by massive physical laten...
Recently I came across a discussion about AI crawlers and robots.txt files. The conversation centered on a simple question:
Should website owners allow AI systems to access their content?
One proposed configuration looked something like this:
User...
Or: how I learned a machine might introduce us before my website ever does.
Every few years, the internet reinvents discovery.
Directories gave way to search engines. Search engines gave way to social feeds. Social feeds gave way to recommendation ...
The Future of Autonomous Camelid Infrastructure
For too long, enterprises have struggled with fragmented camelid workflows. Llamas in one pasture. Alpacas in another. Vicunas trapped behind legacy monolithic fencing solutions.
As organizations sca...
When I first introduced the Sovereign Systems Specificationhttps://kenwalger.github.io/sovereign-system-spec/ and released the initial foundation of the SDK, sovereign-core and its accompanying sovereign-fastapi integration layer see announcement pos...
In our previous series, we built the Sovereign Vault to verify truth in existing records. But as we move deeper into the age of AI, we face a massive unsolved problem: the unstructured nightmare of human history. Millions of documents exist as "silen...
Where this fits: This article extends the Zero-Glue series. If you haven't read The End of Glue Code: Why MCP Is the USB-C Moment for AI Systemshttps://www.kenwalger.com/blog/ai/mcp-usb-c-moment-ai-architecture/, the USB-C analogy below will make mor...
A vault of 3,150 Markdown files is just a very organized digital attic. It’s a repository of every conversation, code snippet, and research rabbit hole I’ve navigated with AI over the last two years, but until now, it was static. It was "organized," ...