Posts
All my articles, thoughts, and ideas.
-
Verity: The Truth Engine Underneath XAP
Published:• 14 min readA close read of verity-engine — five Rust crates, seven trust properties, and the design invariants that turn an agent settlement decision into a record any third party can independently replay.
-
XAP: The Settlement Layer for Autonomous Agents
Published:• 10 min readA close read of XAP (eXchange Agent Protocol): six primitive objects, one transaction flow, and what it takes to make agent-to-agent commerce verifiable without any human in the loop.
-
AgenticMemory, Part 3: The Capabilities That Required a New Data Structure
Published:• 9 min readFour things that are only possible because of the typed cognitive graph — finding connections, simulating what breaks, auditing gaps in reasoning, and recognizing patterns across completely different domains.
-
AgenticMemory, Part 2: How the Agent Searches and Knows What Matters
Published:• 8 min readSelf-correction without data loss, exact-term search that actually works, hybrid retrieval that uses both signals, and a way to find which beliefs everything else is built on.
-
AgenticMemory, Part 1: The Memory Your Agent Was Always Missing
Published:• 10 min readFour foundational capabilities that give AI agents a real brain — not a search bar. The binary format, the portable file, the typed events, and the reasoning chains.
-
Building a Payment System That Proves Finality Instead of Asserting It
Published:• 11 min readMost payment platforms tell you a transaction succeeded. I am building one that proves it — cryptographically, deterministically, and in a way that can be replayed and audited years later. Notes from the work in progress.
-
Building a Memory System for AI Agents
Published:• 22 min readVector databases tell you what is similar. They do not tell you what happened, what was decided, or what the agent learned that overrides what it knew before. I needed something different.
-
Building a Web Cartographer for AI Agents
Published:• 21 min readI wanted AI agents to understand the web the way a researcher does — not just fetch a page, but navigate structure, follow intention, and remember where they have been. Notes from building Cortex.
-
Building Risk Intelligence Systems That Institutions Can Trust
Published:• 12 min readLessons from building AI-powered vulnerability detection for financial institutions and supply chain operators. The hard part is never the algorithm.
-
Why Explainable AI Matters for Financial Regulation
Published:• 11 min readThe case for transparency in AI-driven credit and risk decisions affecting millions of Americans. Not just for compliance — for doing this right.
-
What the Risk Professionals Are Saying About AI
Published:• 7 min readNotes from the GARP Charlotte Chapter Meeting on Artificial Intelligence: Risk, Governance, and Emerging Challenges — November 5, 2025.
-
What I Saw Judging at HackNC 2025
Published:• 8 min readSeven hundred students, eighty projects, and one team of five that built something I will not forget for a long time. My experience judging at HackNC 2025 at UNC Chapel Hill.
-
What I Took Away from the IEEE ENCS Leadership Summit at Duke
Published:• 6 min readReflections from a full day at Duke University with IEEE Region 3's Eastern North Carolina Section. Semiconductors, agentic AI, open access publishing, and the people making it all happen.
-
The Credit Invisible Crisis: How AI Can Bridge the Gap
Published:• 12 min read45 million Americans lack credit scores. Here is what that actually means, why it keeps happening, and how open-source AI frameworks can change it.
-
The Night I Told My Friends About Ifa and AI
Published:• 8 min readA casual Saturday evening with friends turned into a two hour conversation about artificial intelligence, ancient Yoruba divination, and why the future of computing might have roots older than any of us realized.
-
Rethinking Supply Chain Planning with Probabilistic AI
Published:• 14 min readMost supply chain software treats uncertainty as noise to be smoothed away. I've been building something that treats it as the actual input. Some thoughts on why deterministic MRP is fundamentally broken and what a better model looks like.