Long-form articles on AI engineering, covering topics such as monitoring LLM systems, evaluating agentic systems and context engineering. Posts explain concepts mechanically, include diagrams, and are occasionally paired with workshops run by the author.
Website: https://www.newsletter.swirlai.com
A practitioner's newsletter on running AI coding agents in real workflows, covering provider usage limits, billing quirks, failover between Claude and Codex, and reasoning-effort settings. Posts mix first-hand incident write-ups with concrete commands, benchmark figures and decision rules.
A day-by-day hands-on course on building an AI evaluation harness from scratch, with lessons on golden datasets, regression tracking, policy verdicts and CI gating. Each lesson explains the design decision, shows verified results from test runs, and builds on earlier days.
A practical guide to building an LLM wiki, a Markdown-based memory layer for agents, in three phases from ingesting local files to continual learning. Also covers engineering topics such as context quality checks before LLM calls and multi-agent coding workflows.
A developer's blog on AI-assisted and agentic engineering in Elixir, with practical posts on testing patterns, Neovim tooling and code generation. Readers get opinionated, code-backed explanations of how the author builds and uses small open-source tools.
One short email a week with hand-picked newsletters from the index. Free, no spam, unsubscribe anytime.
