Library · Season 1
Building & deploying domain intelligence.
Tutorials and engineering labs, organized as libraries. Every video comes with its chapters, the written version, and the code, data or evaluation behind it — including what failed.
Latest · Lab · Fine-Tuning LabDeploy Your Own AI Model to the Cloud — Qwen + Modal + vLLMRun Qwen locally with Unsloth, then deploy it to an NVIDIA T4 on Modal with vLLM behind an authenticated API and call it from Python — with the cold-start wait, token usage, access checks and the ten-cent bill measured on screen.Watch with chapters →Libraries
Pick a path.
Start hereIntelligence from ZeroThe model is not the AI system.2 published · 9 plannedFine-Tuning LabFine-Tuning LabBaseline first. Held-out eval before adaptation.2 published · 10 plannedFor companiesAI Integration for CompaniesSystematize → Automate → Track → Scale with Agents.0 published · 5 plannedHarnessHarness & Production AIModels create capability. Harnesses create reliability. Evals create evidence.0 published · 12 plannedBuild JournalIntelligenceOS Build JournalWhat was attempted, what failed, what the evidence showed.0 published · 3 planned
All videos
Latest videos.
Coming next
On the schedule.
11 Nov 2026AI Integration Stage 1: Systematize Before You AutomateAI Integration for CompaniesSystems
14 Nov 2026Hyperparameters That Actually MatterFine-Tuning LabLab
18 Nov 2026Operational State Modeling: Turning Business Workflows Into SystemsAI Integration for CompaniesSystems
21 Nov 2026Fine-Tune a Model End-to-End with UnslothFine-Tuning LabLab


