Skip to main content -
The automated repair command was one step from corrupting ten old tickets
-
I stopped babysitting the browser, then had to build the part that was missing
-
Before you repair data, build the diagnostic
-
I Built the Review Tool, Then Told Everyone to Stop Using It.
-
The GoDaddy "No Public API" Myth: Reverse-Engineering the DCC Internal DNS Endpoint
-
rtk Wasn't Broken, It Was Unreachable: How I Found 366 Silent Failures in My AI Agent Sessions
-
When a work queue stops telling the truth
-
Where does the daemon live? Reusing a scheduled-task tick instead of always-on infra
-
A hash-chained manifest makes archive changes visible
-
The dormant-project tripwire: make the unknown visible
-
The epic said "Not started" while six tickets shipped under it: reading progress past a stale status table
-
My agents quietly hoarded 48 GB of Chrome profiles until the machine froze
-
Three compounding bugs spawned a burst of near-identical tickets, and `tail -15` hid the evidence
-
Measure the Bottleneck Before Blaming the Visible Workload
-
My Agent's Chrome Was Running but Invisible: A Windows Session 0 Isolation Ghost Story
-
I bolted a review overlay onto a Classic ASP app
-
One-Flag Fix: --isolated Stops Parallel Playwright Clones From Deadlocking
-
I split my personal cockpit out of the product and everything got cleaner
-
When AI Makes Analysis Cheap, Your Decision UI Becomes the Bottleneck
-
The dashboard got better the moment I stopped centering sessions
-
The useful part of a vault portal was admitting the ai should read, not write
-
My agents needed a filing system before they needed more intelligence
-
The first useful agent teammate needed a Gmail account
-
I killed my clever vault hierarchy in one day
-
I closed a client ticket from the wrong repo on purpose
-
/add-dir Doesn't Reach Across Your Skills: The IDE-vs-CLI Claude Code Gotcha
-
Bootstrapping a New Agent Station, and Giving It a Phone
-
When a Manual Workflow Hurts in Seven Small Ways, the Seven Ways Are Your Spec
-
The One-Shot Data-Repair Script as a First-Class Artifact
-
When a Content Workflow Needs Explicit State
-
RTK Ate My JSON and Hid My Merge Commit: When a Token-Saving Filter Lies to Your Agent
-
I Built a Triage Cockpit Because Context Switching Was Eating the Day
-
Do Not Defer on a Vibe: Use Named Decision Triggers
-
When Working Notes Become Operational Infrastructure
-
A Backlog State Should Tell You What Happens Next
-
If Your AI Workflow Only Exists in Comments, You Have Exhaust
-
How to Triage an 880-Ticket Backlog Without Deleting Real Work
-
When a Workflow Gap Needs an Operator Tool: Preview, Policy, and an Audit Trail
-
Closing a Ticket From a Machine That Never Cloned the Repo
-
Your Committed Output Is a Free Golden Test
-
Your JIRA Session Won't Cross Into an Iframe. Here's the Reused-Popup Workaround.
-
I Was About to Write a digest_job.py. The Platform Already Shipped It.
-
Reverse-Engineering Claude Code's Session JSONL (So You Can Mine Your Own Transcripts)
-
When the Paywall Flow Is Broken, Build the Staff Tool, With Dry-Run, a Cap, and an Audit Row
-
The workflow broke in the glue code, not the AI
-
Your Best Coder Will Be Your Lowest AI Adopter
-
The token-killing proxy I tested instead of trusting my own discipline
-
After seven hours, I couldn't remember which model I was talking to
-
The Fastest Legacy Hotfix Is Often a Diagnostic
-
The Agent Owns the Browser, or You Do
-
The most valuable line in an agent's ruleset: verify the fix in the browser before claiming it's fixed
-
Writing an AI_CONTEXT.md So Your Assistant Stops Rediscovering Your Codebase
-
Teaching the AI to Find the Real Source File: .cursor/rules as a Compiled-Asset Map
-
Same SHAs in Two Repos: Why Commit-Count Metrics Lie in a Clone Workflow
-
MOCK_INFERENCE=1: ship every LLM feature with an env-var kill switch on day one
-
A code-first schema audit: keeping a 1,477-line ASP file in sync with a 14,536-column DB