Route 01 · 12 chapters
Customer-Ready AI Systems
A 12-stage field guide for taking an AI workflow from Python prototype to a secure, operable customer deployment.
Start here
From Python Prototype to Reliable AI API
Tier9AI field notes
Engineering AI that survives production.
Follow a sequence, not a feed. These field guides connect architecture decisions to customer trust, reliable operations, and evidence of business value.
Open the series
Route 02 · 9 chapters
LLM Infrastructure From First Principles
A practical path from models, tokens, and GPU sizing to production inference, intelligent routing, and Kubernetes.
Start here
Why AI Infrastructure Is a Career Move Right Now
Route 03 · 3 chapters
Agent Systems and AI Economics
Architecture and measurement patterns for giving AI systems useful reach, reliable know-how, and accountable business outcomes.
Start here
MCP vs Agent Skills: Reach, Know-How, and the Controls Between Them
Latest notes
Recently published
Technical patterns, operating decisions, and field-tested questions for teams putting AI to work.
Customer-Ready AI Systems
Sep 2, 2026
From Python Prototype to Reliable AI API
A practical guide to FastAPI, asynchronous work, stable errors, webhooks, API styles, and third-party SDK boundaries for production AI systems.
8 min
LLM Infrastructure From First Principles
Sep 2, 2026
Why AI Infrastructure Is a Career Move Right Now
Learn why reliable model serving sits at the intersection of software, distributed systems, performance engineering, and business outcomes.
8 min
LLM Infrastructure From First Principles
Sep 2, 2026
Running llm-d on Kubernetes in Production
Turn the series into a deployment plan using llm-d routing, Well-Lit Paths, Kubernetes workload choices, observability, and scoped hands-on labs.
10 min
Agent Systems and AI Economics
Sep 2, 2026
MCP vs Agent Skills: Reach, Know-How, and the Controls Between Them
A practical guide to deciding when an AI system needs MCP, a Codex Skill, or both—and how to keep the resulting workflow accountable.
8 min
Customer-Ready AI Systems
Sep 2, 2026
Customer Integrations That Survive Production
Design OAuth2, SAML and SSO, SaaS API adapters, signed webhooks, and retry behavior that remain dependable after the demo.
9 min
Customer-Ready AI Systems
Sep 2, 2026
Multi-Tenant AI Without Data Leaks
Compare tenant identifiers, row-level security, schemas, databases, and partitioning patterns for customer-facing AI systems.
8 min
Customer-Ready AI Systems
Sep 2, 2026
Security and Compliance for Customer-Facing AI
Build a practical baseline for SOC 2 readiness, GDPR and HIPAA scoping, PII handling, encryption, and useful audit logs.
9 min
Customer-Ready AI Systems
Sep 2, 2026
Permission-Aware RAG for Customer Data
Design secure ingestion, document-level access controls, permission filtering, citation tracking, and deletion for retrieval-augmented generation.
9 min
Customer-Ready AI Systems
Sep 2, 2026
Repeatable AI Deployments with Docker, Kubernetes, Helm, and CI/CD
Turn an AI application into a versioned, testable deployment that can create consistent customer environments without manual heroics.
9 min