ai

• Why I Ship the Demo Before I Ever Make the PitchJune 24th, 2026
• The Generator Script That Wasn't: A PixelLab Regen Recipe for When Your AI Sprites Get ClobberedJune 20th, 2026
• What Building Email 👍/👎 Taught Me About Feedback LoopsJune 16th, 2026
• My Model Bake-Off Lied to Me Twice — Here's the Methodology That Fixed ItJune 13th, 2026
• How a Security Audit Taught Me to Budget AI Costs in Code (Not Prompts)June 12th, 2026
• Why My Dashboard's Python Runtime Has Never Imported an LLMJune 11th, 2026
• Live Things3 Ranking with Local Ollama — The Cache Trick That Made It WorkJune 7th, 2026
• Read-Only Runtime, External LLM: How I Got Free AI Email Triage in Apollo DashboardJune 7th, 2026
• Fail-Closed Email Triage: Why My AI Defaults to Silence, Not SurfaceJune 5th, 2026
• How Anthropic's Billing Split Forced a Better Email Triage ArchitectureJune 5th, 2026
• When 'Make It All Searchable' Is the Wrong InstinctJune 3rd, 2026
• How I Built a 12-Stage Pixel-Art Body Transformation with PixelLab AIMay 29th, 2026
• Ditch the Slide-Out: How I Built a ⌘K Floating Command Palette for a Law Practice AppMay 28th, 2026
• Why Your RAG Chunks Don't Know Where They Came FromMay 28th, 2026
• Why Hybrid Retrieval Beat Pure RAG for My AI Assistant's MemoryMay 26th, 2026
• The Empty 200: What ZAI Taught Me About Silent Failures in Multi-Provider AI RoutingMay 24th, 2026
• The Ref Trick That Cured My AI Chat's Stale Context ProblemMay 21st, 2026
• Why I Stopped Choosing Between Semantic and Keyword SearchMay 12th, 2026
• Why the 'Best' Model Failed My Meeting Scanner — And What I Use InsteadMay 7th, 2026
• The Request Body That Could Empty Your AI BudgetApril 28th, 2026
• The AI Was a Doorman. No Wonder Nobody Came In.April 27th, 2026
• How a 71% Bounce Rate Taught Me to Scope AI Gates PreciselyApril 24th, 2026
• I Gated the AI to Capture Leads — Then Watched 71% of Users Walk OutApril 22nd, 2026
• Why I Stopped Using Voyage for Text RAG (and When I'd Reach for It Again)April 22nd, 2026
• Why I Ended Up with One JSON Parser for Two Different LLM ModelsApril 14th, 2026
• The AI Recommendations Looked Great. The Data Was Lying.March 27th, 2026