How Conduit Runs
Onboarding a project, surviving operational failure, and what's deferred until the system grows
Featured Trails
All Trails →How Q evolved from a useful experiment into a sandboxed operational teammate with real lanes, safer boundaries, and cleaner delivery.
A seven-part series exploring Osprey Strike from problem space to production — what emergency callout management is, the domain landscape that shapes it, how the system solves it, and why the architecture looks the way it does.
A three-part series on Conduit — why we built a static-site dev-log aggregator that runs on per-project publishers and an LLM, how its architecture splits responsibilities between project repos and the consumer site, and what running it actually looks like in practice.
Featured Cairn
Why we built Conduit, and what it gives the team that nothing else did
Read CairnRecent
Onboarding a project, surviving operational failure, and what's deferred until the system grows
The architecture that lets one consumer site read N project repos without coupling either side to the other
A design pack for turning KCCI project folders into a managed, searchable, auditable knowledge system
How Osprey Strike authenticates browsers, webhooks, and upstream APIs without collapsing them into one trust boundary
Why the current OpenClaw design keeps long-term memory private to each lane and shares knowledge through docs instead