# Ryan Lindsey

> Agentic engineering is making engineers dramatically faster. I build the instruments that let the organization around them keep pace. Nineteen years in software, a decade of it leading engineering teams: I own incident management for an entire engineering organization, I build the agentic tooling that other managers choose to adopt, and I still ship the code. The habit underneath all of it is to measure a process before improving it, because the constraint is rarely where everyone assumes it is.

## Resume

- [Resume (Markdown)](https://ryanlindsey.me/resume.md): Portable markdown résumé -- the cleanest format for a model to read.
- [Resume (JSON)](https://ryanlindsey.me/resume.json): JSON Resume schema, machine-readable.
- [Resume (PDF)](https://ryanlindsey.me/resume.pdf): Print-formatted résumé.
- [Resume (HTML)](https://ryanlindsey.me/resume): The résumé as a web page.

## MCP

- [MCP server](https://mcp.ryanlindsey.me/mcp): Model Context Protocol server with eight tools (get_contact, get_resume, list_case_studies, get_case_study, list_writing, get_post, search_writing, request_private_access) and two resources (resume://json, writing://{slug}). A private tier exists for scoped tokens; request_private_access explains how to ask.

## Site

- [Ask my agent](https://ryanlindsey.me/chat): A grounded chat over everything published here: it answers from the résumé, the case studies and the posts, and cites the page each claim comes from.
- [How this site runs](https://ryanlindsey.me/ops): Live operations: what this site has served over the last 30 days, which models it spends on, how it degrades, and what shipped -- every figure labelled with the system it was read from.
- [AI policy and risk register](https://ryanlindsey.me/ai-policy): What the AI features here do, what they store, for how long, and what they never touch -- with the risk register that backs it, every row carrying a review date.

## Writing

- [Agents that deliver across repositories](https://ryanlindsey.me/writing/armature.md): Armature is a Claude Code plugin that gives an agent a GitHub Projects board to work from: it picks the next item across every repository the board covers, claims it, works it on a branch, and opens a pull request it is not allowed to merge. Why it is shaped that way, and what publishing it cost.
- [An agent-native personal site on Cloudflare](https://ryanlindsey.me/writing/agent-native-site.md): Two Workers, a Model Context Protocol server, a resume in four formats, and 791 tests. What this site is built from, and the five findings that cost the most to learn, four of which are versions of one sentence: a green check is not evidence.
- [A terminal built for driving agents](https://ryanlindsey.me/writing/terminal-setup.md): The macOS terminal I use to keep shipping code as an engineering leader. Ghostty, zsh with Sheldon and Starship, the Rust CLI replacements, and a Claude Code configuration tuned for reviewing agent work you were not present for. Every file copy-pasteable, every opinion marked as one.

## Case studies

- [A green run is not proof: building an agent platform around silent failure](https://ryanlindsey.me/work/silent-failure.md): A production coaching agent for a sim racing team, built solo on Cloudflare and Claude. Every control in it exists because something failed without saying so.
- [Replacing guessed delivery dates with calibrated forecasts](https://ryanlindsey.me/work/delivery-forecasting.md): An agent-native forecasting tool for engineering managers that grew from a set of Claude Skills into an internal MCP server, and ended up inside the org's roadmapping process.

## Full content

- [All content (llms-full.txt)](https://ryanlindsey.me/llms-full.txt): Every published document's markdown in one file -- one fetch instead of one per page.