Category
AI Engineering
I build AI systems for a living. These posts cover what it actually takes to get models, agents, and pipelines into production — the architecture decisions, the failure modes, and the patterns that work across industries.
What You'll Find Here
- Production-focused implementation patterns for AI Engineering.
- Architecture and tooling decisions that hold up beyond prototypes.
- Evaluation and reliability practices to keep AI systems trustworthy.
- Focused tracks: Agents & Automation, LLMs in Production, Data & ML Pipelines.
Subcategories
Agents & Automation
Multi-agent systems, LangGraph workflows, tool use, and autonomous AI pipelines.
LLMs in Production
Taking language models from prototype to production — RAG, evaluation, hallucination mitigation, and deployment.
Data & ML Pipelines
Databricks, SageMaker, feature engineering, model training, and ML infrastructure.
All Articles
How AI Works: From Data to Decisions — A Developer's Introduction to AI Systems
A developer's guide to how AI works end to end: defining the decision, preparing data, training or selecting a model, running inference, applying deterministic product controls, and monitoring real outcomes in production.
Why Most AI Projects Die Before Production (And It's Not a Tech Problem)
The most-cited AI failure stat is made up, but the real numbers are worse, and the reason is almost never the technology.