Your Box and Your Trust Model
What runs on your machine, and how much rope you give the agent — one has a project answer, the other is yours
Library
Knowledge by Topic
All cairns organized by topic. Each article may appear under multiple tags.
AI 24 cairns
Working in Parallel (Mostly)
Worktrees, the bd worktree warning, and the one Docker constraint we have not solved yet
Timbers, the Ledger
The second ledger every commit needs — one line of what, why, and how, searchable forever
The Workshop
A map of every tool between you and a shipped pull request, and where each one comes from
Quiet Power Tools
RTK, tokf, and the small CLI multipliers that compound across every session
Quality Gates: The Contract That Lets You Move Fast
Lint, types, tests, coverage, audits — the deterministic constraints that make agent-driven work safe to ship
Just: One Place to Discover
The discovery surface that turns project incantations into a known place humans and agents both look first
How We Build Here
What's changed about writing production software, and what this trail is going to teach you
From Plan to Pull Request: A Day on Strike
One realistic feature, end to end, with every prior cairn put to work
Codex as Second Opinion
When a single model is bluffing or stuck, a second model is the cheapest unblock available
Claude Code as Daily Driver
The agent harness most of us reach for first, what we run inside it, and the alternatives that are perfectly fine
Beads, the Backbone
The CLI issue tracker that gives an agent a memory that survives the next compaction
The Work That Writes Itself
Why we built Conduit, and what it gives the team that nothing else did
How Conduit Runs
Onboarding a project, surviving operational failure, and what's deferred until the system grows
How Conduit is Shaped
The architecture that lets one consumer site read N project repos without coupling either side to the other
From Intake Folder to Project Memory
A design pack for turning KCCI project folders into a managed, searchable, auditable knowledge system
Three Memories, One Q
Why the current OpenClaw design keeps long-term memory private to each lane and shares knowledge through docs instead
The Only Locked Door
How OpenClaw gives Q a real computer without letting public channels rewrite the machine it runs on
Surviving the Upgrade
What happens when the ground shifts under a running AI agent — and how three days of misdiagnosis led to a five-minute fix
Timbers
A Development Ledger for the Age of AI Agents
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
The Memory Problem
Why AI Agents Forget Everything and What To Do About It
The Injection Problem
Defending LLM agents against prompt injection when they read the world
The Quiet Teammate
What Happens When an AI Agent Picks Up the Work Nobody Owns
Architecture 19 cairns
Boundary Objects for Operational Software
How ECOs, job numbers, statuses, and timelines carry meaning across teams that do not share a tool
How Conduit is Shaped
The architecture that lets one consumer site read N project repos without coupling either side to the other
The Last False Complete
Why field workflows need a soft-complete state before they earn the right to be done
From Intake Folder to Project Memory
A design pack for turning KCCI project folders into a managed, searchable, auditable knowledge system
Three Gates, One Identity
How Osprey Strike authenticates browsers, webhooks, and upstream APIs without collapsing them into one trust boundary
Three Memories, One Q
Why the current OpenClaw design keeps long-term memory private to each lane and shares knowledge through docs instead
The Only Locked Door
How OpenClaw gives Q a real computer without letting public channels rewrite the machine it runs on
Two Tenants, One ECO
Why Osprey Strike needs a two-dimensional tenancy model instead of a generic SaaS checkbox
Surviving the Upgrade
What happens when the ground shifts under a running AI agent — and how three days of misdiagnosis led to a five-minute fix
Timbers
A Development Ledger for the Age of AI Agents
The Lakehouse
What Osprey Vantage is actually building, and why it looks the way it does
When the Fiber Goes Dark
The emergency callout problem in outside plant fiber construction
What's Next
Where Osprey Strike stands today, what's coming, and the questions that still need answers
The Shape of the System
How Osprey Strike is structured, from mono-repo to multi-tenant
The Memory Problem
Why AI Agents Forget Everything and What To Do About It
The Injection Problem
Defending LLM agents against prompt injection when they read the world
The ECO Lifecycle
From outage detection to field resolution — how an emergency callout moves through the system
Running in Production
From Cloudflare edge to PostgreSQL — how Osprey Strike deploys, authenticates, and scales
Events All the Way Down
Event sourcing and CQRS in Osprey Strike — the architecture, the migration, and the escape hatch
Business 5 cairns
Where the Work Lives
Coordinating between GitHub and beads, for the people doing the planning and the people doing the building
The Lakehouse
What Osprey Vantage is actually building, and why it looks the way it does
From Contractor to Operator
How O&M agreements and CLEC licensing are reshaping who runs fiber networks
When the Fiber Goes Dark
The emergency callout problem in outside plant fiber construction
What's Next
Where Osprey Strike stands today, what's coming, and the questions that still need answers
Culture 8 cairns
Where the Work Lives
Coordinating between GitHub and beads, for the people doing the planning and the people doing the building
How We Build Here
What's changed about writing production software, and what this trail is going to teach you
From Plan to Pull Request: A Day on Strike
One realistic feature, end to end, with every prior cairn put to work
Codex as Second Opinion
When a single model is bluffing or stuck, a second model is the cheapest unblock available
Claude Code as Daily Driver
The agent harness most of us reach for first, what we run inside it, and the alternatives that are perfectly fine
The Work That Writes Itself
Why we built Conduit, and what it gives the team that nothing else did
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
The Quiet Teammate
What Happens When an AI Agent Picks Up the Work Nobody Owns
DevOps 18 cairns
Where the Work Lives
Coordinating between GitHub and beads, for the people doing the planning and the people doing the building
Working in Parallel (Mostly)
Worktrees, the bd worktree warning, and the one Docker constraint we have not solved yet
Timbers, the Ledger
The second ledger every commit needs — one line of what, why, and how, searchable forever
The Workshop
A map of every tool between you and a shipped pull request, and where each one comes from
Quiet Power Tools
RTK, tokf, and the small CLI multipliers that compound across every session
Quality Gates: The Contract That Lets You Move Fast
Lint, types, tests, coverage, audits — the deterministic constraints that make agent-driven work safe to ship
Just: One Place to Discover
The discovery surface that turns project incantations into a known place humans and agents both look first
From Plan to Pull Request: A Day on Strike
One realistic feature, end to end, with every prior cairn put to work
Beads, the Backbone
The CLI issue tracker that gives an agent a memory that survives the next compaction
The Work That Writes Itself
Why we built Conduit, and what it gives the team that nothing else did
How Conduit Runs
Onboarding a project, surviving operational failure, and what's deferred until the system grows
How Conduit is Shaped
The architecture that lets one consumer site read N project repos without coupling either side to the other
Three Gates, One Identity
How Osprey Strike authenticates browsers, webhooks, and upstream APIs without collapsing them into one trust boundary
Surviving the Upgrade
What happens when the ground shifts under a running AI agent — and how three days of misdiagnosis led to a five-minute fix
Timbers
A Development Ledger for the Age of AI Agents
The Shape of the System
How Osprey Strike is structured, from mono-repo to multi-tenant
Running in Production
From Cloudflare edge to PostgreSQL — how Osprey Strike deploys, authenticates, and scales
The Quiet Teammate
What Happens When an AI Agent Picks Up the Work Nobody Owns
Domain 10 cairns
Boundary Objects for Operational Software
How ECOs, job numbers, statuses, and timelines carry meaning across teams that do not share a tool
Fiber Industry Acronym Finder
A table-based quick reference rebuilt from the Fiber Industry Notion database
Two Tenants, One ECO
Why Osprey Strike needs a two-dimensional tenancy model instead of a generic SaaS checkbox
The Lakehouse
What Osprey Vantage is actually building, and why it looks the way it does
From Contractor to Operator
How O&M agreements and CLEC licensing are reshaping who runs fiber networks
When the Fiber Goes Dark
The emergency callout problem in outside plant fiber construction
What's Next
Where Osprey Strike stands today, what's coming, and the questions that still need answers
The Shape of the System
How Osprey Strike is structured, from mono-repo to multi-tenant
The ECO Lifecycle
From outage detection to field resolution — how an emergency callout moves through the system
Events All the Way Down
Event sourcing and CQRS in Osprey Strike — the architecture, the migration, and the escape hatch
Operations 2 cairns
Boundary Objects for Operational Software
How ECOs, job numbers, statuses, and timelines carry meaning across teams that do not share a tool
The Last False Complete
Why field workflows need a soft-complete state before they earn the right to be done
Security 10 cairns
Your Box and Your Trust Model
What runs on your machine, and how much rope you give the agent — one has a project answer, the other is yours
Quality Gates: The Contract That Lets You Move Fast
Lint, types, tests, coverage, audits — the deterministic constraints that make agent-driven work safe to ship
Three Gates, One Identity
How Osprey Strike authenticates browsers, webhooks, and upstream APIs without collapsing them into one trust boundary
Three Memories, One Q
Why the current OpenClaw design keeps long-term memory private to each lane and shares knowledge through docs instead
The Only Locked Door
How OpenClaw gives Q a real computer without letting public channels rewrite the machine it runs on
Two Tenants, One ECO
Why Osprey Strike needs a two-dimensional tenancy model instead of a generic SaaS checkbox
Surviving the Upgrade
What happens when the ground shifts under a running AI agent — and how three days of misdiagnosis led to a five-minute fix
The Injection Problem
Defending LLM agents against prompt injection when they read the world
Running in Production
From Cloudflare edge to PostgreSQL — how Osprey Strike deploys, authenticates, and scales
The Quiet Teammate
What Happens When an AI Agent Picks Up the Work Nobody Owns
Tools 24 cairns
Where the Work Lives
Coordinating between GitHub and beads, for the people doing the planning and the people doing the building
Your Box and Your Trust Model
What runs on your machine, and how much rope you give the agent — one has a project answer, the other is yours
Working in Parallel (Mostly)
Worktrees, the bd worktree warning, and the one Docker constraint we have not solved yet
Timbers, the Ledger
The second ledger every commit needs — one line of what, why, and how, searchable forever
The Workshop
A map of every tool between you and a shipped pull request, and where each one comes from
Quiet Power Tools
RTK, tokf, and the small CLI multipliers that compound across every session
Just: One Place to Discover
The discovery surface that turns project incantations into a known place humans and agents both look first
How We Build Here
What's changed about writing production software, and what this trail is going to teach you
From Plan to Pull Request: A Day on Strike
One realistic feature, end to end, with every prior cairn put to work
Codex as Second Opinion
When a single model is bluffing or stuck, a second model is the cheapest unblock available
Claude Code as Daily Driver
The agent harness most of us reach for first, what we run inside it, and the alternatives that are perfectly fine
Beads, the Backbone
The CLI issue tracker that gives an agent a memory that survives the next compaction
The Work That Writes Itself
Why we built Conduit, and what it gives the team that nothing else did
How Conduit Runs
Onboarding a project, surviving operational failure, and what's deferred until the system grows
How Conduit is Shaped
The architecture that lets one consumer site read N project repos without coupling either side to the other
From Intake Folder to Project Memory
A design pack for turning KCCI project folders into a managed, searchable, auditable knowledge system
Three Memories, One Q
Why the current OpenClaw design keeps long-term memory private to each lane and shares knowledge through docs instead
The Only Locked Door
How OpenClaw gives Q a real computer without letting public channels rewrite the machine it runs on
Fiber Industry Acronym Finder
A table-based quick reference rebuilt from the Fiber Industry Notion database
Surviving the Upgrade
What happens when the ground shifts under a running AI agent — and how three days of misdiagnosis led to a five-minute fix
Timbers
A Development Ledger for the Age of AI Agents
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
The Memory Problem
Why AI Agents Forget Everything and What To Do About It
The Quiet Teammate
What Happens When an AI Agent Picks Up the Work Nobody Owns
Workflow 1 cairn
The Last False Complete
Why field workflows need a soft-complete state before they earn the right to be done