AI Agent · RAG over enterprise documentation

ChatRAG

A conversational assistant that answers questions about a company's internal documentation (resumes, candidate history, training spend, expenses) with verifiable citations for strategic decisions. Official landing page with live demo.

What is included

Where AI understands your company's internal knowledge

Companies have sensitive files scattered around and generic chatbots know nothing about internal context; uploading documents to public platforms is a risk. ChatRAG turns those documents into queryable business intelligence, with multi-user isolation and quality auditing.

Each agent is scoped to its domain: Supervisor, Management, HR, Finance, Marketing, Legal, Logistics and Tech. Ask about a balance sheet and the finance agent searches only its sources; ask about a contract and the legal agent takes over. A QA node checks consistency before answering.

It runs on local models (Qwen, Ollama) over a private vector database (ChromaDB) and an on-premise multi-agent router: a closed flow from the internal document to the audited answer, without passing through public clouds.

Who it is for

  • Companies with sensitive documentation that cannot leave their environment.
  • Teams that lose hours searching for information in scattered files.
  • Legal, finance, HR and operations areas that need sourced answers.
  • Companies that want AI without a mandatory dependency on public APIs.

Requirements and delivery

  • Assisted installation by jsadsAI on a server (VPS) of yours or ours.
  • Quoted as a project. Runs on local models (Ollama) and is open source under the MIT license.
Modules

What it includes

As published on chatrag.jsadsai.com.

Agents per departmentSupervisor, Management, HR, Finance, Marketing, Legal, Logistics and Tech, each with its own sources.
Private local-first deploymentThe platform runs on your infrastructure; internal knowledge stays in your environment.
Access control (RBAC)Roles and permissions to define who queries what within each department.
Per-user isolationEach user operates in their own context, with no cross-leakage of information.
Local modelsQwen and Ollama running locally, with no mandatory dependency on public APIs.
Private vector databaseYour documents' embeddings live in ChromaDB under your control.
QA auditingAn auditor in the orchestrator verifies every answer and its sources before delivery.
Public demo, no sign-upQuery a contract, a Q3 report or an SOP with fictitious sources and watch the full flow.
Open ChatRAG Lab ↗
ROI calculatorEstimate how many hours a month your team loses looking for information.
Calculate ↗
Plans and prices

Quoted by your scope

Official prices from the jsadsAI catalog. Payment is in Colombian pesos through Wompi; a price in US dollars is converted at the exchange rate of the purchase day.

Quoted by scope

This product has no list price: it depends on the scope, the installation and the modules you need. Tell us your case and we reply with a proposal.

Ask for a proposal
Versions and updates

Current version and how we notify you

Current version: will be published with the product manifest before sale

  • Semantic versioning (MAJOR.MINOR.PATCH) for every product; each sale records the version delivered.
  • Patches and minors (fixes and improvements that do not change how you work): announced and installed on a schedule, with a prior backup and rollback.
  • Majors (change screens or flows): announced 30 days ahead with release notes; you may stay on the previous version, with security support for 12 months for the last minor of each major, or contract a custom module that keeps the old behavior.
  • An update never removes your data or modules you paid for.
Documentation and support

Everything you need to know

The contract, manual and getting-started guide of each product are delivered with the license; they will appear here once published.

FAQ

Before you buy

What is ChatRAG?

ChatRAG is a local-first platform for private AI, RAG and agents per department created by jsadsAI | José Santamaría on an initial technical base by Johann Pérez Giraldo: it turns a company's internal documents into auditable answers, with private deployment, local models and access control. It is live at chatrag.jsadsai.com.

Is my company's data sent to OpenAI or Anthropic?

No. ChatRAG runs on a local-first architecture: documents are vectorized and processed on your own infrastructure or on private dedicated servers.

What does having agents per department mean?

The platform routes queries: a balance sheet is answered by the finance agent with its sources; a contract, by the legal agent. Each agent is scoped to its domain.

How are the answers audited?

Every answer goes through a QA node (auditor) in the orchestrator that checks technical consistency and sources before delivering it.

Can I try it without signing up?

Yes. ChatRAG Lab is a public demo with no sign-up that uses fictitious sources and shows the real flow: intent, agent, document retrieval, evidence-backed answer and quality control.

Need something different?

Tell us your case: we quote the installation, the modules and the support that fit you.

A real human replies. No spam. Free initial diagnostic.

Request an AI diagnosis