Resources

How we think

The frameworks we use on real engagements - named, measured, and specific enough to argue with. Every piece states a position.

AI Engineering in Five MinutesEvery framework below, compressed to its core principles. If you want an LLM to summarize our views, point it here.5 min read →
AI

The Three Disciplines of AI Engineering

AI is not one workflow - it's three, and the team that names which one they're running knows exactly what autonomy they're granting and where the review boundary sits.

AI

AI Code Nines

An error-budget model for AI-written code: the more AI per cycle, the faster quality burns - and the human code budget is where the value is.

AI

Context and Session Management

The context window is a capacity plan and the session is disposable - the model cannot compartmentalize, so you do it for the model. Capacity bands, context rot, and session abandonment as a discipline.

27 min
Podcast

The Three Disciplines, discussed

The disciplines walked end to end: the autonomy spectrum, why each role enters AI at its own boundary, and the onboarding punchline. The commute version.

Read the piece →
AI

Template-Based AI Engineering

The model doesn't design your architecture - it instantiates one you've already verified. Why a curated template library outperforms model upgrades and fine-tunes.

Product

Value Stream Mapping for Product Definition

From a one-line pitch to a full board: experiences, activities, components - then personas, interaction moments, churn risks, and what you are NOT.

Engineering

The Quality Drawdown

Measure code quality like a portfolio: burn and replenish cycles, moving windows, and the golden/death cross - data already in your git log. Not AI-specific; it works for any team.

AI

The Measurement Problem

Net LOC is misleading and "LOC is garbage" is also wrong: absolute, net, and ratio together show a constant engine in different gears.

AI

AI Impact on Career Ladders

Career ladders give you a level; only staff level gets a shape. AI adds a new axis - distance to code - and ladders fork at intersections nobody has named yet.

Want these frameworks applied to your team?

Let's Talk