Writing
Field notes from production agent infrastructure
Long-form, code-first writing on cutting LLM costs, building evals, and making codebases ready for agents. No thought-leadership fluff.
- 3 min readdevexplatform
Standardizing AI coding tools without killing autonomy
How DevEx and platform leaders turn a Claude Code / Cursor / Copilot free-for-all into a golden path — shared slash commands, agent definitions, MCP access, and review hooks — without mandating a single way to work.
Read - 3 min readctostrategy
The “add AI” mandate: a CTO’s first 90 days
The board wants AI in the product and you have to commit before the bets are proven. A sequencing playbook for CTOs — what to ship first, how to handle build-vs-buy, and how to keep costs forecastable.
Read - 3 min readsecurityai-code
Securing AI-generated code: a checklist for security leaders
AI is writing code faster than anyone can review it. A practical checklist for CISOs and AppSec leaders to control AI-generated code, prompt data leakage, and new injection surfaces — without slowing the team down.
Read - 3 min readevalsquality
You shipped AI features with no evals. Here’s how to fix that.
Most teams shipped production AI with zero evaluation. This is how to add evals incrementally — without stopping the roadmap — so prompt and model changes stop being blind deploys.
Read - 3 min readagentic-devcodebase
Is your codebase agent-ready? A scoring rubric
Agents thrive in some codebases and thrash in others. Here is the rubric we use to score how ready a codebase is for agentic development — and what to fix first.
Read - 4 min readllm-costsobservability
How to cut LLM costs 30–60% without losing quality
A practical, vendor-agnostic playbook for finding and removing 30–60% of your production LLM spend — model routing, caching, batching, and the observability to keep it gone.
Read