Length 4–7 minutes
Structure Hook → Problem → Insight → Demo → Takeaway
Cadence Biweekly
Season 1

What the Best Practitioners Actually Do

For developers experimenting with AI tools

S01E01

Your Claude.md Is Fighting You

Overloaded context files degrade output quality. The practitioners who get the best results use minimal, precise context — not maximal instructions.

S01E02

Stop Repeating Yourself to AI

If you're making the same correction twice, you've identified a standard. The question is whether you capture it or keep correcting manually forever.

S01E03

The Skill Is the Correction, Not the Prompt

Prompt engineering is a dead end. The real skill is recognizing when output deviates from intent and correcting precisely. That's the signal that matters.

S01E04

What a Standards File Actually Looks Like

Walk through a real standards file from a real project. What each rule does, where it came from (a correction), and how it changes AI output quality.

S01E05

Skills vs. Standards vs. Context: Know the Difference

The three things people stuff into Claude.md serve different purposes and should live in different places. Clarify the taxonomy.

S01E06

Why Vibe Coding Plateaus

Vibe coding works for prototypes. It stalls when you need consistency, architectural compliance, and accumulated knowledge. That's the wall GlideCoding solves.


Season 2

From Personal Practice to Team Knowledge

For tech leads and engineering managers

S02E01

Your Senior Engineers Are Governing Already

Every code review correction is a governance artifact that disappears into a PR comment. The knowledge exists — it's just not captured.

S02E02

The Onboarding Problem Nobody Talks About

New developers using AI tools reproduce every mistake the team has already solved. Without captured standards, organizational knowledge resets with every new hire.

S02E03

How Corrections Become Standards

The mechanism: a correction is captured, confirmed across contexts, reviewed by a senior practitioner, and promoted to a team standard. A real example, end to end.

S02E04

Measuring What AI-Assisted Development Actually Produces

Lines of code is meaningless. Correction rate, standard adoption, and architectural compliance are the metrics that tell you whether AI tooling is helping or hurting.

S02E05

The Institutional Memory Problem

AI has no memory between sessions. Every conversation starts from zero. The organizations that solve this aren't prompting better — they're building a standards layer.

S02E06

Why Your AI Governance Can't Live in a Doc

Policy documents drift. Standards files that are enforced structurally don't. The shift from documentation to enforcement is the maturity leap.


Season 3

Governance as Architecture

For CTOs, platform leads, and architects

S03E01

Models Execute. Systems Govern.

The foundational thesis. Governance cannot live inside the model. It must be external, structural, and independent of the execution layer.

S03E02

The Authority Hierarchy

User constraints are binding. Preferences carry strong weight. Agent discretion only exists where the user hasn't spoken. Walk through the three levels.

S03E03

Why Multi-Model Consensus Matters

Single-model governance is a single point of failure. Critical decisions should require agreement across independent models before execution.

S03E04

The Confused Deputy Problem in AI Agents

When an agent acts with inherited authority it hasn't earned, you have a confused deputy. How to prevent it architecturally.

S03E05

Earned Autonomy, Not Granted Autonomy

Agents should earn operational freedom through demonstrated compliance, with regression protection that revokes autonomy when standards are violated.

S03E06

The 12-Layer Governance Stack

A comprehensive governance architecture for AI-assisted operations. Each layer serves a distinct function. Most organizations have 3–4 layers. They need 12.


Don't miss an episode.

Videos, essays, and practitioner notes delivered biweekly. No spam. Unsubscribe anytime.

You're in. We'll send the first dispatch soon.

No spam. Unsubscribe anytime.