[verdict][generated prompt][source: lex.page]
Can I vibecode Lex?
// one session, and a personal version you can actually use
The core loop is small enough for a capable coding agent to produce a useful local version in one sitting. For Lex, write and revise long-form documents with comments, version history, and AI actions. The hard boundary is collaborative editor polish, sync, and embedded model access, plus workflow, data, and model tuning.
confidence: high
what it is: Write and revise long-form documents with comments, version history, and AI actions
Buildability index · an editorial game
- Price 12 $/month weight: plus 2
- Time multi-day weight: plus 1
- Category ai writing no weight
- Moat execution quality · collaboration weight: minus 2
- Confidence high weight: plus 1
- What you lose 5 items weight: minus 2
- Site lex.page (si apre in una nuova scheda) no weight
They cancel out. This is where it comes down to how much the subscription annoys you.
Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.
What you build
Take a brief, gather user-supplied source material, generate and revise a structured long-form draft with comments and AI actions, and keep citations and version history attached to each section.
what you need
- OpenAI API key
- Node.js 22
- local or self-hosted deployment
- user-supplied sources
Editorial comparison targets the Pro plan and a personal content workstation DIY substitute. Recheck price before merge.
The prompt
One session with a coding agent and your version runs.
Build a personal replacement for Lex in an empty repository.
Use Next.js 15, TypeScript, Tailwind CSS, SQLite, Drizzle ORM, and the OpenAI Responses API; do not offer alternative stacks.
The core loop is: take a brief, gather user-supplied source material, generate and revise a structured long-form draft with comments and AI actions, and keep citations and version history attached to each section.
Make the first run work locally with one documented command.
Store all user data locally by default and make export straightforward.
Put secrets in .env, ship .env.example, and never commit credentials.
Build a brief form with audience, objective, tone, source URLs, and prohibited claims.
Store imported source text locally and chunk it for retrieval with SQLite FTS5.
Generate an outline first and require approval before drafting sections.
Attach source references to generated paragraphs and flag unsupported claims.
Provide rewrite controls for shorten, clarify, change tone, and add evidence.
Export clean Markdown plus a JSON research bundle.
Include clear empty, loading, success, and recoverable error states.
Add input validation, safe filenames, and graceful handling of unavailable APIs.
Write focused tests for the core transformation and one end-to-end happy path.
Create a README with setup, architecture, permissions, data location, and backup steps.
Do not add accounts, billing, telemetry, analytics, or a hosted control plane.
Deliberately leave out live search-engine rank data.
Deliberately leave out automatic publishing to third-party CMSs.
Deliberately leave out multi-user approvals and brand governance.
Finish by running the tests and listing the exact commands used.Prompt generated from the data on this page, not reviewed by hand yet. In English on purpose — it is the language coding agents work best in.
What you lose
- collaborative editor polish, sync, and embedded model access
- proprietary ranking data
- brand-trained models
- team workflows
- large template libraries
Why people still pay
People still pay for Lex because the subscription bundles a refined workflow, proprietary signals, templates, and predictable output quality for a team. The recurring cost buys prompt maintenance, retrieval quality, source handling, provider changes, and editorial QA, not just the visible interface.
moat: Execution quality Collaboration what a moat is
workflow, data, and model tuning
Free alternatives
Not in the mood to build it? These already exist, they are free or open source, and we checked them one by one.
Rejected (1) — and why
- AFFiNE (si apre in una nuova scheda) — Docs and comments are free, but AI becomes paid after seven days and free cloud history lasts only seven days.
Who has already built it
Starting from here is still vibecoding: the prompt is for when you want it exactly your way.
- Open WebUI (opens in a new tab) — Active open-source interface for local and API-backed language models with retrieval features.
Do you agree?
The vote balance
Ancora nessun voto: il tuo è il primo.
Nessun voto ancora — il primo pesa.
