Ron Itelman

Excited to be learning about jev, a new and needed paradigm is continuing to gain momentum. To be clear, were following similar strategies (and have been before jev) with the W3C Context Graph Community Group

Without a shared definition of context it is extremely difficult to manage it across silos.

Much of the industry is now focused on providing more context to models: larger context windows, RAG, memory, and better prompting. These are important. The category error is treating them as the context problem without first making "context" itself computationally measurable.

What is context? Can you answer what is in cell d8? Decide before you read on... The answer is that this is a map of the sky and d8 refers to a different map. That missing information, revealed to you which changed your understanding, is context.

Major breakthrough! By using the four facets of the context graph, was able to demonstrate the gauge can predict which missing information to ignore to safely make decisions. Calling it decision shapes for now.

Context saves money because time, effort, and tokens aren’t wasted in avoidable misunderstandings. Context is the process of identifying what information is missing, for making better decisions and coordinating correctly. This is what we're working on in the W3C Context Graph Community Group.

Banksy Museum in Madrid...

Unifying Business, Data, and Code is getting translated to Chinese!

The Four facet model for AI data product observability is simple and effective.

“.. U.S. margin debt rose 54% to a record $1.4 trillion in May .. “.. Leveraged funds bought $300 billion in derivatives since March ..” @wsj.com www.wsj.com/finance/stoc...

Unless you can explain how your benchmark handles ambiguity, using agents to merge datasets, and touting your own benchmarks aren't ready for others to trust.

The circular relationships, dependencies, and expectations of trillions in revenue, with plenty of evidence to the contrary makes it hard to fathom exuberance in markets. Feels like dominoes are about to fall...

"Government by organized money is just as dangerous as Government by organized mob." —FDR, 1936

When people ask me how to get started in R&D, innovation, or skunkworks, I do my best to help. I am saddened that leaders are willing to take high risk bets in AI while employees get little to no support for their ideas to experimented on with little risk to them.

Frame: an agent's way of reading messages: the interpretive setting a message is read against. It lives with the agent, not in the message. Framing: the act of supplying a receiver the frame a message did not carry ("let me give you context"), changing how the receiver reads what it already has.

The four facet model is the foundation of the w3c context graph community group protocol. Without making these four facets explicit, you introduce dark uncertainty which no policy of a model can manage, specifically with communication between nodes in a network. It is generalizable and scale-free.

Forward Deployed Engineers and ontologies are hot. But before you buy an AI solution: • How is accuracy measured? • How is complexity minimized? • How hard is it to leave? Building an open standard & looking for pilot partners to benchmark the above with the W3C Context Graph CG spec.

Would you like to learn about intent mapping for the W3C Context Graph CG spec? DM me!

We have *never* before seen consumer sentiment this low.

Suzanne Vega releases “Luka” 39 years ago this weekend. She said she once received a fan letter about it: “Dear Suzanne, Luka is the most compelling piece of music I’ve heard in a long time. There are no words 2 tell U all the things I feel when I hear it. I thank God 4 U, Prince”

Leaders can mistakenly assume alignment exists because strategy has been communicated. But in reality, people align to individual incentives, budgets, and KPIs long before they align to organizational goals. Systems can appear stable in isolation while failing in coordination.

I remember watching the science of bubbles in a documentary, and it was mesmerizing to watch the slow-motion hole on the surface of the bubble spread out across until the stability of the entire structure collapsed all at once.

Has lean solves waterfall issues? Will AI solve ______ issues? Not if those issues: Mainly coordination in complex networks, made explicit and testable, are not addressed.

What we're working on, in the w3c context graph community group...

The reason AI projects struggle with implementation is that same that has been a challenge for all software development. We have different reference frames, which give us valid reasons to make decisions within those frames. But an organization doesn't live in one frame. Those differences? Context.

@stevenstrogatz.com 10 years ago your TED talk on sync changed how I think. It led me to a new theorem on unverifiable configurations at system boundaries. The unexpected finding: some errors aren't random — they phase-lock to the calendar (date format ambiguity fires on days 1–12 of every month)

Schrodinger's revenue: Two columns, one word

Everyone claims to own semantics — ontologists, knowledge graph engineers, Decision Intelligence. They're all right, inside their own systems. The W3C Context Graph CG formalizes the liquid space between them — the boundary no one owns.

You depend on systems you can't see inside: "Revenue" in one means gross. In another, net. If nobody checks if intent is coherent, a blast radius risk silently grows. The W3C Context Graph Community Group is building a protocol to tell you what's aligned, what's unknown, and what to do.

I wrote this song on Saturday, recorded it yesterday and released it to you today in response to the state terror being visited on the city of Minneapolis. It’s dedicated to the people of Minneapolis, our innocent immigrant neighbors and in memory of Alex Pretti and Renee Good. Stay free

"Soldiers are cutting us down, should have been gone long ago.” 2024 Rock Hall Inductee Dave Matthews recently covered the Crosby, Stills, Nash & Young protest anthem “Ohio” while on tour in Mexico. youtube.com/shorts/tcsAt...

Decision traces are about modeling a user's understanding in decision making...

Exploring concepts of confidence, conviction, and trust from a product design perspective...

Working on context graphs and organizational intelligence? I've got tools, methodology, and experience to help, please reach out!

There's a lot of buzz around context graphs and I want to introduce the idea of intent maps. Intent Maps are real time and inherently feedback loops of the user defined meaning for diff operations against ontologies and system rules. I've opened sourced core libraries, please reach out!

My belief is that the intent management layer is missing from most companies attempts to build reliable AI solutions.