Notes from the studio.
Engineering notes on AI, ML, custom apps, and the messy bits of shipping production software.
What AI Agents Can Actually Do for Your Business in 2026
AI agents are real, useful, and easy to oversell. Here is a plain-English look at what they do well today, where they still need a human, and how to start.
Cut Your LLM Bill Without Cutting Quality
A practical, ordered playbook for lowering production LLM costs. Prompt hygiene, caching, model routing, retrieval, budgets, and the measurement that ties it all together.
Do You Actually Need Custom AI, or Is an Off-the-Shelf Tool Enough?
A straight, vendor-neutral answer to the question every founder is asking right now. Most teams do not need custom AI yet. Here is how to tell when you do.
How to Build a RAG Assistant That Actually Answers From Your Company Docs
A practical, vendor-neutral guide to building an AI assistant grounded in your own handbook, policies, and support history, plus the failure modes to avoid.
Building Neutral AI: How We Ship Production Systems Without the Hype
Hype-free engineering principles for AI products that serve users, not nudge them. Grounding, refusal, evals, cost-bounding, the boring decisions that actually ship.
AI Development in 2026: When to Use RAG, Fine-Tuning, or Just Better Prompts
A practical AI development guide, when retrieval-augmented generation beats fine-tuning, when prompt engineering wins, and the cost equation most teams skip.
Custom App MVP Development: What 4 Weeks Actually Buys You
What you can realistically ship in a 4-week custom app MVP, features, tradeoffs, and the timeline traps that kill startups.
Machine Learning in Production: Beyond the Jupyter Notebook
A working model is not a working product. The full production ML stack, data pipelines, deployment patterns, monitoring, drift detection.