Articles & Deep Dives

The complete archive of our thoughts, essays, and rigorous analysis. Discover in-depth research on enterprise engineering, artificial intelligence, and digital strategy.

engineeringRecently Published

The Agent Reliability Problem: Why Your Multi-Step AI Keeps Breaking

A 95%-reliable step chained ten times is ~60% reliable. The Reliability Tax explains why agent demos collapse in production and how to architect around it.

operationsRecently Published

The Team You Actually Need to Build AI (It's Not Who You Think)

Teams staff AI as if ML talent is the scarce ingredient. The Capability Triangle — product, engineering, domain — shows the missing vertex is usually domain.

strategyRecently Published

The Pilot Trap: Why Your AI Never Leaves the Lab

Most AI gets stuck in perpetual piloting. The Production Gradient turns the leap to production into a path of stations with exit criteria, so pilots graduate.

engineeringRecently Published

Evals Are the Product: The Test Suite That Decides Whether Your AI Survives

In AI the eval suite is the product — the only thing telling you whether a change helped or hurt. The Evaluation Pyramid: unit, capability, behavior, outcome.

designRecently Published

When the Model Is Wrong: Designing AI for the Failure You Know Is Coming

A probabilistic system will be wrong in production. The Failure Ladder — prevent, detect, contain, recover, learn — designs the response, not just detection.