Problem
Recruiters and their AI agents need resume data they can read, verify and query, not only a PDF.
Approach
One typed data module drives every surface (page, JSON-LD, resume.json, CV files, agent tools); search and tools run in the browser against the published data.
Result
19 agent tools, and CVs in 2 languages as PDF (3 focus versions), Word and Markdown, generated from the same data on every release.
Architecture
- Astro static site in English and Spanish; one typed data module (resume.ts) feeds the HTML, JSON-LD, resume.json, the PDF/DOCX generators and the agent tools.
- On-device semantic search: passage embeddings (multilingual-e5-small) are precomputed at build time and only the visitor’s query is embedded in the browser with Transformers.js on WebAssembly.
- 19 WebMCP tools: 12 imperative tools registered with document.modelContext (navigator.modelContext in older browser builds; also exposed as window.oscarResume) and 7 declarative <form toolname> tools that also work as plain HTML forms.
- CV pipeline: Puppeteer prints the /print/ route to PDF (a default version and two focus versions) and html-to-docx builds the Word file, in both languages, on every release; all of them, and the Markdown CV, are rendered from one CV model (scripts/lib/cv-model.ts).
- Quality gates: Vitest unit tests, Playwright end-to-end and axe accessibility tests, Lighthouse CI budgets and a CV regression check run in GitHub Actions.
Key decisions
- Static first: every agent capability runs in the browser against resume.json, so the site needs no server to work.
- Precompute passage vectors at build time and download the ~135 MB model only when the visitor turns semantic search on, so it never blocks rendering or uses data by default.
- JSON-LD is generated from the same data as the page, so search engines and agents see the same facts as people.
- A Zod schema validates the resume data before every build, so broken dates or missing translations fail the build instead of shipping.
- Built with AI-assisted coding and review (Claude Code), under strict TypeScript and that pre-build content check.
Outcomes
- 19 agent tools
- 2 languages, 10 CV files per release (6 PDF, 2 Word, 2 Markdown)
resume-oscarenas.web.app/