Reference Library

Guides

Durable, maintained references on building agent systems that behave in production. Updated as the ground shifts.

A Glossary of Agent Architecture

Forty-two terms defined precisely enough to argue with, including which ones get routinely conflated and why the distinction matters.

Updated Aug 10, 2026 · 10 min

Agent Failure Modes: A Taxonomy

Hallucination is not a useful category. Twenty-one ways agent systems actually break in production, grouped by where the failure originates.

Updated Aug 9, 2026 · 8 min

Buy, Build, or Wait: Evaluating AI Capability as a CTO

The decision before tool evaluation. Three options, not two — and in a fast-moving market, choose for cheap reversal rather than best expected value.

Updated Aug 14, 2026 · 7 min

Hallucination Is a Data Contract Problem

Trace a wrong number back and you rarely find a model inventing it. You find an undefined term, an unstated grain, an ambiguous null, or a stale snapshot.

Updated Aug 11, 2026 · 8 min

How to Evaluate an AI Tool for Your Business

The scores in any comparison expire. The method does not. How to run the evaluation yourself and reach a decision you can defend in six months.

Updated Aug 9, 2026 · 9 min

Letting an Agent Touch the Warehouse Safely

Read replicas, query budgets, row limits and closed egress paths — the layers that turn an arbitrary query from a non-deterministic caller into a bounded operation.

Updated Aug 11, 2026 · 7 min

Making an Agent Explain What It Did to Your Data

A generated explanation is not evidence. Capture the path mechanically — query, as-of, row counts, definitions — and assemble the explanation from the record.

Updated Aug 11, 2026 · 7 min

Shadow Mode: How to Deploy an Agent That Can't Hurt You Yet

Real production traffic, real decisions, no consequences. How to run an agent in shadow, how to grade it, and how to set the promotion threshold before you look at the data.

Updated Aug 10, 2026 · 10 min

Technical Debt in the Age of Generated Code

Writing code was never the constraint. Generation collapsed the cheap half of the problem and left comprehension exactly where it was.

Updated Aug 14, 2026 · 7 min

The Agent Reliability Handbook

What it takes to run an agent in production without it quietly breaking things. Contracts, blast radius, replay, and the checklist before you give it write access.

Updated Aug 8, 2026 · 12 min

Threat Modeling an AI Agent

Conventional threat models assume data and instructions stay separate. Agents dissolve that boundary by design. Here is how to model one properly.

Updated Aug 9, 2026 · 9 min

Tool Contracts: The Interface Between a Reasoning System and the Real World

A tool description is the entire world model a reasoning system uses to decide whether to fire an irreversible action. The nine things a contract has to declare.

Updated Aug 10, 2026 · 10 min

What Horse Racing Taught Me About Model Confidence

Being right is not the goal. Knowing how often you are right is. Calibration, edge, staking, and the discipline of the pass.

Updated Aug 8, 2026 · 9 min

What to Ask Before Approving an Agent Deployment

Nine questions whose answers are hard to fake, each with what a real answer sounds like and what a hand-wave sounds like.

Updated Aug 14, 2026 · 7 min

Why LLMs Are Bad at Big Data

Language models produce plausible text, not correct numbers. Why bigger context windows do not fix it, and the architecture that does.

Updated Aug 8, 2026 · 11 min