← S.P. — FIELD NOTEBOOK EXP-005 · FIELD SHEET

ONE WORKER · ONE DEPLOY · ZERO RESUMES STORED

Your resume never leaves the edge. The verdict does.

LAUREL turns an uploaded resume into a structured career report with an honest quality score, then a curated shortlist of six roles with match scores, skill gaps, and concrete first steps. Documents are read entirely in the browser; the only thing that crosses the wire is text, answered by Groq LPU inference behind a single Cloudflare Worker. Nothing is ever stored.

RESUMES STORED
0
PDF/DOCX read client-side
DEPLOY UNIT
1
Worker serves API + SPA together
SHORTLIST
6
roles, scored with skill gaps
RESEARCH RECORD
94%
skill extraction — see EXP-005

A / THE ARCHITECTURE

The whole service is one Worker.

BROWSER — REACT 19 SPA PDFJS / MAMMOTH EXTRACT TEXT ONLY LEAVES CLOUDFLARE WORKER "LAUREL" — HONO /API/PARSE · /API/RECOMMEND · STATIC ASSETS EVERY MODEL FIELD NORMALIZED + CLAMPED GROQ LPU LLAMA 3.3 70B · JSON THE WORKER SERVES THE FRONTEND VIA STATIC ASSETS — ONE DEPLOY SHIPS THE ENTIRE SERVICE.
Fig. A — errors are typed and human-readable: 400 invalid, 422 not-a-resume, 429 rate-limited, 502 upstream.

B / THE CONTRACT

Three endpoints, no surprises.

METHODPATHBODYRETURNS
GET/api/healthservice status
POST/api/parse{ "text": "<resume text>" }{ "resume": ParsedResume }
POST/api/recommend{ "resume": ParsedResume }{ "jobs": [...], "insights": ... }

C / ENGINEERING NOTES

Fast because it's private.

CODE ON GITHUB ↗ BACK TO EXP-005 REACT 19 · HONO · CLOUDFLARE WORKERS · GROQ