Thought Leadership

Writing

Thoughts on agentic AI, context engineering, data architecture, and the future of intelligent systems. Deep dives from 25+ years at the cutting edge.

Featured Series

The Autonomous Stack

A 4-part series on the architecture of truly intelligent systems — from the data substrate to agent runtimes to prescriptive intelligence. Built from real experience with MemoryOS.

Part 1

The Data Layer

Nobody's building it

Part 2

The Runtime Wars

Agent OS architectures

Part 3

Reactive to Prescriptive

The proactive agent shift

Part 4

The Stack That Thinks

Putting it all together

Featured Series

Agent Societies

A 4-part series exploring what happens when agents interact at scale—from emergence to institutions. Grounded in real observations from Moltbook.

Part 1

The Petri Dish

When agents build societies

Part 2

Reinforced Learning

Why most will fail

Part 3

Emergence to Competence

PAR, world models, economies

Part 4

Looking Ahead

12 agent-native institutions

Featured Series

Building SemanticStudio

An 8-part deep dive into building a production-ready multi-agent chat platform—from chat UX to self-learning ETL pipelines. Formerly AgentKit.

View Series Overview

Part 1

Introduction

Why I built SemanticStudio

Part 2

Chat Experience

Sessions, files, preferences

Part 3

Multi-Agent

28 domain agents

Part 4

RAG Config

Models and modes

Part 5

Memory

4-tier architecture

Part 6

GraphRAG

Knowledge graph

Part 7

ETL & Agents

Self-learning pipelines

Part 8

Production

Quality & observability

Featured Series

Results as a Service

A 2-part deep dive into outcome-based business models and the architecture that makes them real—from Result Contracts to Internal RaaS.

Part 1

Why 2026 Is the Year

Outcomes become the product

Part 2

RaaS Architecture

The control plane that makes it real

Featured Series

The AI-Native Computer

A 3-part series exploring how AI is reshaping enterprise architecture—from LLMs as the new CPU to BDAT playbooks for the AI-native enterprise.

Part 1

The New Computer

LLMs as CPU, tokens as bytes

Part 2

AI as Front End

From screens to capability graphs

Part 3

BDAT Playbook

Architecting the AI-native enterprise

The Autonomous Stack · Part 4 of 4

The Stack That Thinks: Putting It All Together

The Autonomous Stack is four layers: data substrate, agent runtime, proactive intelligence, and human interface. When all four work together, intelligence compounds.

April 5, 202610 min read

AI ArchitectureAI StrategyAgent ArchitectureEnterprise AIFuture of Computing

The Autonomous Stack · Part 3 of 4

From Reactive to Prescriptive: The Proactive Agent Shift

Today's agents wait to be asked. Tomorrow's will tell you what you're missing. The shift from reactive to prescriptive is where agents become genuinely valuable.

March 29, 20269 min read

AI ArchitectureAgent ArchitectureAI SystemsMemory SystemsAI Strategy

The Autonomous Stack · Part 2 of 4

The Runtime Wars: Agent Operating Systems Are Here

Agent runtimes have crossed from frameworks to operating systems. ZeroClaw, OpenFang, and OpenClaw represent three competing philosophies for giving agents a durable lifecycle.

March 22, 202610 min read

AI ArchitectureAgent ArchitectureAI SystemsOpen SourceSecurity

The Autonomous Stack · Part 1 of 4

The Data Layer Nobody's Building

Vector stores and RAG are table stakes. Real agent intelligence needs a continuous, multi-modal data substrate with episodic, semantic, relational, temporal, and contextual data.

March 15, 20269 min read

AI ArchitectureData StrategyAgent ArchitectureMemory SystemsContext Engineering

Agent Societies · Part 4 of 4

Looking Ahead: 12 Agent-Native Institutions Nobody's Talking About

Here's what gets built when agents can form institutions. These are the 'StackOverflow 2.0s' that turn messy questions into verified artifacts.

February 22, 20268 min read

AI ArchitectureAgent SocietiesInstitutionsProduct Strategy

Agent Societies · Part 3 of 4

From Emergence to Competence: PAR Loops, World Models, and Agent Economies

Societies generate priors. World models generate consequences. Verification generates truth. Here's the architecture that turns emergent behavior into emergent competence.

February 15, 20267 min read

AI ArchitectureAgent SocietiesPAR LoopsWorld Models

Agent Societies · Part 2 of 4

Reinforced Learning Environments: Why Most Agent Networks Will Fail

Emergence isn't enough. Most agent societies will collapse into confident sludge. Here's what separates the ones that compound from the ones that collapse.

February 8, 20266 min read

AI ArchitectureAgent SocietiesEmergenceVerification

Agent Societies · Part 1 of 4

The Petri Dish: When Agents Build Societies

I've been watching agents build a society. The emergent behaviors appearing when large numbers of agents interact without human orchestration point to something bigger than better chatbots.

February 1, 20266 min read

AI ArchitectureAgent SocietiesEmergenceMulti-Agent Systems

Building SemanticStudio · Part 1 of 8

SemanticStudio: A Production-Ready Enterprise RAG Agent System

Open-sourcing the multi-agent chat platform I built to test my AI-native architecture ideas. 28 domain agents, 5 configurable modes, 4-tier memory with Context Graph, GraphRAG-lite, and everything enterprises need to build production AI.

January 26, 20268 min read

SemanticStudioMulti-Agent SystemsRAGEnterprise AIOpen Source

Building SemanticStudio · Part 2 of 8

The Chat Experience: Sessions, Folders, Files, and More

A complete walkthrough of SemanticStudio's user-facing features—from session management to file uploads to power user shortcuts.

January 26, 20266 min read

SemanticStudioChat UXProduct DesignEnterprise AI

Building SemanticStudio · Part 3 of 8

Domain Agents: Specialization at Scale

Why SemanticStudio uses specialized domain agents instead of one general-purpose assistant, and how to configure and manage them—from 12 to 50+ agents.

January 26, 20267 min read

SemanticStudioMulti-Agent SystemsEnterprise AIAgent Architecture

Building SemanticStudio · Part 4 of 8

RAG Chain Configuration: Models, Modes, and Fine-Tuning

The power user's guide to configuring SemanticStudio's RAG chain—multi-provider LLM support, mode parameters, and full control over cost vs. quality.

January 26, 20267 min read

SemanticStudioRAGLLM ConfigurationEnterprise AI

Building SemanticStudio · Part 5 of 8

Memory as Infrastructure: The Complete 4-Tier System

A deep dive into SemanticStudio's 4-tier memory architecture—working context, session memory, long-term memory, and the Context Graph. Progressive compression meets knowledge bridging.

January 26, 20268 min read

SemanticStudioMemory SystemsContext EngineeringRAG

Building SemanticStudio · Part 6 of 8

GraphRAG-lite: Beyond Vector Similarity

How SemanticStudio's knowledge graph and entity resolution enable relationship discovery that pure vector RAG misses.

January 26, 20268 min read

SemanticStudioGraphRAGKnowledge GraphsRAGEntity Resolution

Building SemanticStudio · Part 7 of 8

ETL & Agent Creation: Growing Your Multi-Agent System

How SemanticStudio's self-learning ETL pipelines ingest data, build knowledge graphs, and automatically create new domain agents.

January 26, 20267 min read

SemanticStudioETLData EngineeringMulti-Agent SystemsSelf-Learning

Building SemanticStudio · Part 8 of 8

Production Quality: Evaluation, Observability, and Trust

What separates demos from deployable systems—SemanticStudio's quality evaluation, hallucination detection, and enterprise observability.

January 26, 20267 min read

SemanticStudioQuality EvaluationObservabilityEnterprise AIProduction

Results as a Service · Part 1 of 2

Results as a Service: Why 2026 Is the Year Outcomes Become the Product

AI agents make outcome delivery feasible. Economic pressure makes it inevitable. Here's what RaaS actually is, where it's already working, and why the shift from 'pay for software' to 'pay for results' changes everything.

January 3, 20267 min read

AI StrategyEnterprise AIBusiness ModelsRaaS

Results as a Service · Part 2 of 2

RaaS Architecture: The Control Plane That Makes Outcomes Real

RaaS isn't a pricing model—it's the commercialization of an execution loop. Here's what Result Contracts look like, how the Outcome Control Loop works, and what providers and consumers need to make outcome-based models real.

January 3, 202615 min read

AI ArchitectureEnterprise AIAgentsRaaS

Stochastic Core, Deterministic Shell: The Enterprise Agent Pattern That Holds Up

A lot of agent talk still sounds like old SaaS talk. In production, the pattern that works is simple: the core is stochastic, the shell is deterministic. You don't trust the agent—you bound it.

December 31, 202512 min read

AI ArchitectureEnterprise AIAgentsProduction Systems

AI-Native Computer · Part 1 of 3

The New Computer Organization: AI Isn't Just an App, It Is the Computer

We're quietly standing up a new computer on top of the old one. In this new computer, LLMs are the CPU, tokens are the bytes, and the context window is the RAM.

December 22, 20257 min read

AI ArchitectureEnterprise AIFuture of Computing

AI-Native Computer · Part 2 of 3

When AI Is the Front End: The Future of Software and SaaS

If AI is the front end and the LLM is the CPU, what does that do to traditional software? Apps stop being destinations and become capability graphs.

December 22, 20257 min read

AI ArchitectureEnterprise AIFuture of Software

AI-Native Computer · Part 3 of 3

Architecting the AI-Native Enterprise: A BDAT Playbook

How should a leading organization design for an AI-native future? Using the BDAT lens—Business, Data, Application, Technology—we explore what's next.

December 22, 20259 min read

AI ArchitectureEnterprise AIEnterprise Architecture

Private AI: The Next Step in Enterprise Intelligence

Why data sovereignty and secure AI architectures are becoming non-negotiable for enterprise AI deployments.

December 10, 20252 min read

AI StrategyEnterpriseSecurity

Context Engineering: Beyond Window Sizes

How to architect RAG systems that overcome attention dilution and recency bias in large context windows.

December 5, 20253 min read

TechnicalRAGResearch

Agentic Architecture: Patterns That Scale

Design patterns for multi-agent AI systems that actually work in production environments.

December 1, 20253 min read

TechnicalAI SystemsArchitecture

Building RAG Systems at Enterprise Scale

Lessons learned from implementing retrieval-augmented generation across hundreds of documents and thousands of users.

November 26, 20252 min read

TechnicalRAGAI Systems

Data Products: The Foundation AI Needs

Why treating data as a product is essential for AI success, and how to build the data infrastructure that makes AI work.

November 22, 20253 min read

Data StrategyAI StrategyEnterprise

Superworkers, Not Replacements: The Future of AI at Work

Why the best AI systems amplify human capabilities rather than replace them. A framework for thinking about AI-augmented work.

November 19, 20252 min read

AI PhilosophyFuture of WorkStrategy

Teaching Machines, Teaching Humans

What 5,000+ students and two decades of AI development have taught me about learning—both artificial and human.

November 16, 20253 min read

TeachingAICareer

Data Governance in the AI Era

How traditional data governance practices must evolve to support AI initiatives while maintaining trust and compliance.

November 14, 20252 min read

GovernanceData StrategyAI