Skip to content

Agentic AI Research

Trust, but Validate

In my formative years working in audit and risk at EY, mostly within life sciences companies, I never once asked a client whether they trusted their ERP system. It would have been a strange question. Nobody trusts an ERP (people have feelings about their ERP, but trust is rarely one of them). What we asked was whether the system was controlled - or, if it was a GxP system, whether it was validated - it was the standard stuff: who had access to what, whether the audit trail was switched on, and what happened the last time something went wrong.

Knowledge That Gets Stronger From Being Wrong

We've come to equate knowledge with wikis, and most wikis are wrong - or at least they will be eventually. That's not a knock on wikis, it's a knock on the assumption underneath them: that the stuff we wrote down is correct. This post is my attempt to argue for a different starting assumption (that it probably isn't) and to explore what a knowledge system looks like if you build it that way from the beginning.

Don't Train Your Model to be an Expert

Real experts mess up sometimes, admit it, and learn faster the next round. If someone never changes their mind, I assume they stopped paying attention.

Many teams still pitch the same idea: "Grab the latest base model, fine-tune it on our data, and boom—we have an expert." The second you do that, the model stops being current, and worse, it freezes your thinking. Knowledge keeps moving; your model should too.

LLMs Don’t Have a Memory Problem — They Have a Provenance Problem

The 2025 Context Engineering Survey, which reviewed more than 200 research papers and enterprise pilots, cautions: “Simply enlarging an LLM’s context window does not guarantee reliable attribution or auditability; we still need explanation systems, audit mechanisms, and governance structures.” (Context Engineering Survey 2025 §4). Put differently, the problem isn’t raw memory capacity — it’s the provenance of the information we cram inside. This is exactly the rationale we followed when designing Context Units for our Pyrana platform.

Context Efficiency

It's funny I've spent years talking about tokens in all of my blockchain work. Whether it be NFTs or stablecoins, it seemed like tokens were everywhere. Now that we're diving in deep and trying to fix some problems with context in AI, it seems the topic of tokens (albeit a very different kind) is still center stage. The phrase "tokenization of the world" has taken on a new meaning to me.

Data Without Context is Useless

Enterprises plough well over $200 billion every year into data-warehouses, BI dashboards, and analytics suites,- and analysts now forecast the big-data analytics market to top $1.1 trillion by 2033¹. Financial-services firms alone spend $44 billion a year just on market-data feeds². Yet studies keep showing that roughly half of the information companies collect never gets used³.

The Role of Content Addressability in Context Units: Building Distributed Knowledge Systems

A technical exploration of how content-addressable storage principles enable robust, distributed knowledge management through immutable context units

Introduction

When we think about things our knowledge flows like water - it's hard to grasp why we know something or where we learned it (we sometimes don't stop to think about if it is even true), yet we are able to draw conclusions that we "think" are right. If we later ask "why did I think that" we can rationalize our thought process to explain/convince others, but that is usually done in hindsight. We like to think that logic and reason guided us to a conclusion, but most of our decisions are just made by our gut and we then justify them later. The more often we turn out to be right the less we are challenged and the more confident we are in our thinking.

Are Enterprise AI Agents just RPA rebranded?

There’s nothing new under the sun… If 20 years of technology consulting has taught me anything, it’s that a good story can be retold forever. Sometimes we just need to update it with the current buzz words or fit it to current the narrative for it to seem relevant. Today’s narrative of choice, of course, is AI. We hear a lot about how enterprise AI agents are going to revolutionize corporate organizations, but when I ask people how, it sounds a lot like the same old story.