AI assistants and search decision
Fonles Studios, Corp.
A capable developer can reproduce a useful RAG-based legal assistant for one user (document ingestion, retrieval, LLM prompts, generation) in ~36 hours, but you would lose Alhelí's curated national datasets, claimed benchmarked quality and enterprise support — those represent durable advantages not delivered by an off‑the‑shelf build.
Visit website↗$30/mo
$360/yr
Read off the official pricing page.
$100one-off36 h to build
$90/mo6 h/mo upkeep
On cash alone, building overtakes the subscription at 4 seats.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Fonles Studios, Corp. alternatives, with the arithmetic →
What a replacement has to do
- User uploads PDFs or describes needed document → system ingests and indexes corpus → retrieval-augmented prompts query LLM → system generates a legally referenced document or answers with citations → user downloads or refines output.
What it still won’t have
- Proprietary, curated national legislation and jurisprudence dataset and its updates
- Any claimed large-scale benchmarks, market position and brand trust
- Enterprise support, priority onboarding and bespoke configuration for 60k-page analyses
- Potential quality improvements from proprietary models or tuned legal models
What remains hard
- Proprietary data
Legislación vigente de Ecuador integrada (100% actualizada)
- Brand trust
Puesto #3 mundial en benchmarks. Tecnología única al alcance de todos.
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 4 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal self-hosted legal-RAG assistant using FastAPI (Python), Postgres for metadata, FAISS (or Milvus) for vectors, Tika + Tesseract for PDF text/OCR, OpenAI or compatible LLM API for generation, and a lightweight React UI. Core features in scope: PDF upload + OCR, chunking and embedding pipeline, vector retrieval, RAG prompt templates returning answers with source citations, DOCX/PDF generation from templates, simple user auth, and an admin endpoint to refresh legal corpus. Out of scope: training custom LLMs and acquiring proprietary national jurisprudence datasets. Include error handling, logging, unit tests for ingestion and retrieval, and deployment scripts (Docker Compose).
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 5 cited sources+3
- Price verified on pricing page+3
- Hard moats found in the evidence-3
- Evidence score60
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 5
Every page the run actually retrieved.
- official productAlhelí — official product
- official pricingAlhelí — Pricing
- official docsAlhelí — Features
- open sourcearc53/DocsGPT
- open sourceaingdesk/AingDesk
Integrity checks
What held up, and what did not.
