Name Resolution Was Never Enough The other half of the discovery problem runs on a machine clock: a workflow engine asking, mid-pipeline, for the current, healthy, authorized version of a specific skill, with no one available to double-check the answer before it executes. Get that resolution wrong in a search box and someone
The Catalog Already Learned to Talk to Machines Every AI asset library needs a way for a person to ask, in plain language, for the prompt or agent they need, or the library just becomes another place things go to get lost. That's not a new problem. Enterprise data catalogs spent most of the last decade
A Person and a Pipeline Are Asking the Same Question Every organization that has moved past a single AI pilot runs into the same inventory problem: a growing pile of prompts, agents, and model versions spread across teams, with no reliable way for a person or a system to find the right one on demand. Left alone, that gap turns
Six Vectors and a Reranker The Oversaturation Problem: Why More Search Vectors Make Retrieval Worse Every retrieval vector in this series earns its place by resolving cases the others get wrong. Past that point, adding another one doesn't add coverage, it adds noise for the reranker to clean up, and the corpus gets harder to filter exactly as it grows large enough to need filtering most.
Six Vectors and a Reranker Policy Doc or Teams Message: Measuring Authority in a Knowledge Base A knowledge base doesn't just retrieve facts, it retrieves claims, and claims come with sources of wildly different quality. The policy doc and the offhand Teams message can say the same thing with completely different authority behind them. Most retrieval systems can't tell the difference.
Six Vectors and a Reranker Permissions Are Not Tags: The Pre-Filter Problem Nobody Names Access control and metadata filtering both narrow the candidate pool before search runs, which makes people treat them as the same mechanism. They aren't, and the difference is exactly where a query classifier can quietly cost you the right answer.
Six Vectors and a Reranker Time Is Not a Timestamp: Fixing Temporal and Graph Retrieval A document's publish date tells you when it was written. It doesn't tell you when the facts inside it stopped being true. That gap is where knowledge management systems get confidently wrong answers, and it's the same gap that makes a graph worth building.
Six Vectors and a Reranker The Six Vectors and the Reranker That Actually Matters Every enterprise knowledge project starts with a request for 'semantic search.' What actually works is six retrieval methods arguing with each other until a reranker decides who's right.
The Agentic Stack The Context Window Is Not a Filing Cabinet The Context Window Is Not a Filing Cabinet Here is what most teams do with the context window: they fill it up. Every prior message, every retrieved document, every system prompt update, every intermediate result piled in until either the model complains about length or performance degrades enough that someone
The Agentic Stack Your Multi-Agent System Has a Coordination Problem Your Multi-Agent System Has a Coordination Problem Single-agent systems have one set of problems. Multi-agent systems have all of those plus a new category: the problems that arise at the boundaries between agents. Who tells whom what to do. How agents share state without corrupting each other&
The Agentic Stack You Can't Improve What You Can't Measure — Agentic Evaluation Done Right You Can't Improve What You Can't Measure — Agentic Evaluation Done Right Most teams know their agent's average quality in the same way they know their own health without a doctor: by how it feels. The code usually looks right. The summaries are usually reasonable.
The Agentic Stack If You Can't Reconstruct What the Agent Did, You Don't Have a System If You Can't Reconstruct What the Agent Did, You Don't Have a System The standard for understanding what happened in a software system is the audit log. In regulated industries it's a compliance requirement. In any production system, it's what you reach
The Agentic Stack How to Stop an Agent That's Gone Wrong How to Stop an Agent That's Gone Wrong The question is not whether your agents will go wrong. They will. Every team that runs agents in production eventually faces a session that's headed somewhere it shouldn't be. The question is what you can do
The Agentic Stack The Error Your Stack Trace Will Never Catch The Error Your Stack Trace Will Never Catch Software engineers are trained to think about errors in terms of exceptions. The process threw. The API returned a 500. The database connection timed out. These are the errors that interrupt execution and produce a log entry. They are also the easiest
The Agentic Stack Agentic Systems That Don't Improve Are Just Expensive Software Agentic Systems That Don't Improve Are Just Expensive Software The pitch for agentic AI is that it compounds. You invest in building a system, the system gets better over time, and the return on that investment grows without proportional additional effort. That pitch is true, but only for
The Agentic Stack Why Your Agent Forgets Everything Every Morning Why Your Agent Forgets Everything Every Morning The most common complaint I hear from teams that have deployed agents into real workflows: "it keeps making the same mistakes." They've seen the failure mode. They've told the agent about it. They've watched it
The Agentic Stack The Orchestration Model You Pick Is the Architecture Decision You Can't Undo The Orchestration Model You Pick Is the Architecture Decision You Can't Undo Teams tend to pick an orchestration framework the way they pick a JavaScript framework: whatever the first engineer already knew, or whatever had the best tutorial. Three months later, they're fighting the architectural constraints
The Agentic Stack The Defect Is in the Definition The Defect Is in the Definition Every software team knows the cost of finding a defect late. The multiplier varies depending on where in the SDLC you catch it, somewhere between 10x and 100x, but the direction is always the same: the later the find, the worse the math. In
The Agentic Stack The Plan Is a First-Class Artifact The Plan Is a First-Class Artifact Ask most engineers how their agent decides what to do next and they'll say "it reasons through it." That's true as far as it goes, and it's precisely the problem. Reasoning through it is not
The Agentic Stack Agentic Development Is Eleven Problems, Not One Agentic Development Is Eleven Problems, Not One Most agent projects fail at the same place and for the same reason. A team picked up one tool, pointed it at a problem, and discovered six months later that the tool only solved one of the eleven things standing between them and
Philosophy & AI Black Box AI Fails Weber's Test Max Weber's sociology of authority identified three types of legitimate power. Traditional authority derives from custom and precedent: we follow because it's always been this way. Charismatic authority derives from the perceived exceptional qualities of an individual: we follow because the person is compelling. Rational-legal
Philosophy & AI You Can Train a Character, Not Just Rules Anthropic's model spec says Claude should be "genuinely helpful, honest, and harmless." That sentence is not a rule. It's a character description. And the distinction matters more than most people discussing AI alignment have recognized. Aristotle's answer to "how do you
Philosophy & AI Design Your AI Like You Don't Know Who You Are John Rawls asked one of the most useful questions in the history of political philosophy: what principles would rational people choose for organizing society if they didn't know what position in that society they would occupy? Behind the "veil of ignorance," you don't know
Philosophy & AI Prompt Injection Is a Use/Mention Confusion. The Architecture Has No Fix. Prompt injection is ranked LLM01:2025, the number one vulnerability in AI applications, according to OWASP's current LLM Top 10. The UK's National Cyber Security Centre has said it "may be a problem that is never fully fixed." Researchers have documented attack success rates
Philosophy & AI The Data Doesn't Pick the Model Willard Van Orman Quine and Pierre Duhem arrived at the same uncomfortable conclusion from different directions: the empirical evidence underdetermines the theoretical choice. Multiple, mutually incompatible theories can fit the same set of observations equally well. The data doesn't tell you which theory is correct. You choose based
