The Journal
What we ship, what breaks, and what actually works. Written by the people doing the work - no ghostwriters, no filler.
More entries
· 11 min read
Self-preference bias in LLM judges, measured: we made 10 frontier models grade each other's work across 839 blind calls, including our own benchmark winner.
llm as a judgellm benchmarkai evaluationclaude opus 5
· 10 min read
Design AI agent approval workflows without vendor lock-in: risk tiers (auto-approve, notify, block-and-ask) plus n8n and MCP implementation sketches.
AI agentsapproval workflowshuman in the loopn8n
· 8 min read
AI enablement consulting services for businesses, from the buyer's side: what you get, engagement models, fixed pricing from $5,000, and 10 vetting questions.
ai enablementai operatorshiring consultantsai adoption
· 9 min read
An AI operator directs AI to produce real work; one person runs 5 sites with 1,000 posts/day capacity. The 6 duties, 5 skills, and a free JD template.
AI operatorAI enablementhiringAI automation
· 9 min read
AI project rescue, defined: a staged recovery framework for stalled chatbots, RAG, and automation pilots, plus how to decide rescue vs rebuild vs retire.
AI project rescuefailed AI projectsAI automationRAG
· 9 min read
What Claude Fable 5 changes for business output: verified benchmarks, the June suspension timeline, real rollout checks, and how one operator runs it.
Claude Fable 5AI enablementAI operatorClaude Code
· 11 min read
A developer's guide to cleaning up AI-generated code: nine recurring smells, before/after fixes, and the safety-net workflow that makes refactoring safe.
AI-generated codecode cleanuprefactoringcode smells
· 9 min read
A senior engineer's triage playbook for broken vibe-coded apps: stabilize, diagnose, then decide refactor vs rewrite, with the risk order that matters.
vibe codingAI-generated codecode cleanuptechnical debt
· 9 min read
Three human-in-the-loop patterns for MCP servers: elicitation, sampling review, and out-of-band approval, plus an open-source server you can run today.
MCPAI agentshuman-in-the-loopping-a-human
· 8 min read
n8n vs Mastra compared by an agency that ships both: visual workflows vs a TypeScript agent framework, when each wins, and how to combine them.
n8nMastraAI agentsworkflow automation
· 8 min read
What a vibe coding cleanup specialist does, what one costs, how to vet them, and when to hire one vs rebuild: a hiring guide from a team doing the work.
vibe codingAI-generated codecode cleanuphiring
· 8 min read
Vibe coding technical debt, quantified: the five debt types AI code accrues, what each costs to carry, and how remediation actually gets priced.
vibe codingAI-generated codetechnical debtcode cleanup