# Build brief — a focused alternative to Saply

> **Verdict:** Partly, if you narrow it · **Buildability:** 46/100 · **Category:** Automation
> **Source:** https://www.canitbevibecoded.com/saply
> Independent editorial assessment from Can It Be Vibe Coded? Not affiliated with, endorsed by, or derived from Saply. Verify current pricing and capabilities before acting.

## Context

**Saply** — AI CV formatting, tailoring, matching, and template automation for staffing firms. It currently costs $230/mo.

A capable coding agent can build the personal core: extract a clean, text-based CV, structure or tailor it with an LLM, and render a branded DOCX. It will work on tidy CVs and silently drop data on the rest. Saply's value is extraction accuracy across thousands of real-world CV layouts, tuned so no field goes missing on a client-facing document, plus the integrations that keep recruiters inside Word, their email, and their ATS.

This brief describes a focused, single-operator replacement for the part of Saply that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.

## What you are building

Upload a text-based PDF or DOCX, extract structured candidate data, optionally tailor it to a job, and render a branded DOCX.

- Automate a small number of known workflows with logs, retries, and manual recovery.
- A responsive interface with real empty, loading, success, and error states.

## Requirements

### Functional

- PDF and DOCX text extraction.
- Tagged DOCX template.
- Document rendering.
- Local job storage.

### Data and integrations

- LLM API key.

Each of these needs a real account, credential, or quota. Set them up before writing feature code.

### Non-functional

- Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
- Security: server-side secrets, validated input, and no credentials in the client bundle.
- Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
- Portability: the operator can export their data and leave without losing it.

## Implementation brief

Build me a local CV formatting pipeline to replace Saply for personal use. Requirements:

- A Node + Express app on localhost:4173 with one page to upload a PDF or DOCX,
  choose a file from templates/, add an optional job description, and run the job.
- Extract DOCX text with mammoth and PDF text with pdftotext. Detect image-only files
  and stop with a clear message instead of producing an empty CV.
- Send extracted text to an LLM API of your choice, key from .env, using a strict JSON
  schema for contact details, summary, skills, experience, education, and certificates.
- Never invent employers, dates, qualifications, or skills. Missing values stay null,
  and every tailored claim must be supported by the source CV.
- Render the JSON into the selected tagged Word template using docxtemplater and PizZip,
  preserving its fonts, colors, tables, headers, footers, and repeating experience rows.
- When a job description is present, show a 0-100 match score, strengths, gaps, and
  questions. Rewrite the summary and bullets only when a Tailor checkbox is enabled.
- Save job metadata and structured JSON in SQLite via better-sqlite3. Delete uploaded
  source files and generated documents after 24 hours.
- Bind to localhost only, with no accounts or telemetry. Data leaves the machine only
  for the documented LLM call.
- Out of scope: OCR for scanned CVs, Word or Google Docs add-ins, ATS/email integrations,
  bulk processing, collaboration, and enterprise compliance controls.
- Include a sample tagged template, two fixture CVs, extraction/render smoke tests, and
  a README covering setup, .env, template tags, retention, and the honest limitations.
- Be aware of the hard part: CVs vary wildly in structure (two-column layouts, tables,
  sidebars, mixed date formats), and a schema that runs fine on the fixtures will
  silently miss fields on real-world CVs. Test on messy inputs and document what gets
  dropped.

## Delivery standard

- Inspect the repository first, then write a short implementation plan before writing code.
- Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
- Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
- Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
- Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
- Add structured logs around every external call and return actionable errors without leaking sensitive details.
- Write unit tests for the core logic and one automated test of the main user journey.
- Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.

## Acceptance criteria

- [ ] A clean install starts the app using only the README and .env.example.
- [ ] The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
- [ ] Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
- [ ] The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
- [ ] Tests, type checking, linting, and a production build all pass with no ignored failures.
- [ ] No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.

## Non-goals

Do not build these, and do not claim to have replaced them:

- Extraction accuracy across thousands of real-world CV layouts, tuned on years of data so nothing is silently dropped.
- OCR for scanned and image-based CVs.
- The AI agent that edits any CV in plain language directly inside Word and Google Docs.
- Word, Google Docs, email, and ATS integrations (Bullhorn, Carerix, Spott, Loxo).
- The useful dataset is owned, accumulated, or expensive to reproduce.
- Connectors, OAuth flows, and vendor API changes require constant upkeep.

## What you still own after launch

- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
- Maintain every third-party integration as APIs and OAuth rules change.

## Risk

**Operational risk.** The code is achievable; dependable data, integrations, and ongoing operations are the real cost.

Editorial confidence in this assessment: high. No independent one-shot implementation is linked yet.

## Prior art

Working open-source software you can read, fork, or borrow from before starting:

- [Reactive Resume](https://github.com/AmruthPillai/Reactive-Resume) — Open-source resume builder with customizable templates and PDF, JSON, and DOCX export
- [Resume Matcher](https://github.com/srbhr/Resume-Matcher) — Open-source LLM resume tailoring, job matching, template editing, and PDF export

---

Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/saply