AI-Native Operating Model
How the full engineering system enables AI-native work. This trail borrows articles from Engineering and Agentic Engineering & Q — each keeps its primary home; here they read as one story.
Start the trail →Parts
-
Part
AI-Native Engineering: Can You Migrate Incrementally?
Why bolting agents onto an unchanged SDLC plateaus at 5–20%, and how the 10x teams rebuilt their operating model
-
Part
The Weekend Knowledge Base
Building a self-improving knowledge system from zero in under 8 hours of actual effort — and what that says about internal tooling in 2026
-
Part 1
The Work That Writes Itself
Why we built Conduit, and what it gives the team that nothing else did
-
Part 2
Beads, the Backbone
The CLI issue tracker that gives an agent a memory that survives the next compaction
-
Part 3
Timbers, the Ledger
The second ledger every commit needs — one line of what, why, and how, searchable forever
-
Part 6
From Plan to Pull Request: A Day on Strike
One realistic feature, end to end, with every prior cairn put to work