Writing · Nº 041065 essays
The writing
Ideas from inside the work. Explore technology, entrepreneurship, and the practice of building things that last.
1065 essays found · Page 50 of 89
Clear filtersAICommon Mistakes When Buying AI AgentsThe most common mistakes buying AI agents: falling for the demo, ignoring failure modes, over-scoping autonomy, and skipping the audit trail. How to avoid each.EngineeringOptimistic UI Needs Server ReconciliationOptimistic UI without server reconciliation is a bug generator. Show the change instantly, but always reconcile against the server's authoritative result.OperatingProtect One Deep Work Block a DayA solo operator running twenty companies cannot clear the whole calendar. Protect one deep work block a day instead, and let AI absorb the reactive noise around it.EngineeringShould You Solve CAPTCHAs or Design Around Them?Most scrapers hit a CAPTCHA because they earned it. Before paying a solving service, learn why you got flagged. Here is when to solve captchas and when to avoid them.StrategyThe Spreadsheet Running Your Agency Is a LiabilityThe master spreadsheet running your agency is a single point of failure with no permissions, no history, and no gates. Here is why it has to go.EngineeringSSH Hardening Checklist for a Production VPSA practical SSH hardening checklist for a self-hosted VPS: keys only, no root login, non-standard config, and the settings that actually stop brute-force attacks.EngineeringWhen Not to Refactor Legacy CodeNot all legacy code should be touched. Learn when refactoring legacy code is a waste of budget and when leaving ugly, stable code alone is the right call.OperatingContractors vs Employees for Agency DeliveryContractors vs employees for agency delivery comes down to whether the work is systematized. Here is when to use contractors and when to hire instead.AIWhen Your AI Should Refuse to AnswerKnowing when your AI should abstain instead of answering is a governance feature. How to build confident refusal, and why it beats a confident wrong answer.EngineeringLLM as Judge: When to Trust It for AI EvaluationUsing an LLM as judge to score AI output is fast and scalable, but it is biased and gameable. When to trust LLM-as-judge for evaluation and when to bring in a human.AIAI B-Roll: Fill the Gaps in Your Edit Without a ShootHow to use AI video as b-roll to fill gaps in an edit: cutaways, establishing shots, and cover footage generated to order instead of hunting through stock libraries.OperatingApproval Gates in Automation: When to Require a HumanNot every step in an AI workflow should run unattended. Here is how to place approval gates so high-stakes actions pause for a human without killing throughput.