JULIEN'S IT SERVICES icon

JULIEN'S IT SERVICES

custom software development

Vasile — knows all your documents

Exact answers from your own documentation, each one with the source cited.

A RAG (Retrieval-Augmented Generation) system takes your documentation, contracts, PDFs, and knowledge base and turns them into an assistant that answers strictly from those materials. It cites its sources instead of making things up, and re-indexes itself when the documents change.

See an example

A prepared conversation, so you can quickly understand how it can help.

I'm Vasile. Ask me anything about Julien's IT Services, and I'll also tell you where the information came from.
What is Julienly?
Julienly is a tool that helps you create websites and presentation pages faster. It's built for founders, small teams, and projects that don't want to wait months before launching. Source: Julienly product description.
And how would a project with you work?
We start with a short conversation to understand what you want to achieve. Then we agree on what needs to be built, work in clear steps, and adjust after launch. The goal is that you always know what's next and when each part is coming. Source: Julien's IT Services working process.
Do you sell physical products too?
I couldn't find that in the documents I have, so I don't want to make up an answer. If you'd like, I can send the question to the team and someone can reply by email.

Try it yourself

You have 5 free messages in this session.

This demo runs on our AI assistant. In real projects, we adapt it to your business, with clear answers, tone, and rules.

Back to all demos
Vasile — knows all your documents
Live demo
from €119/moLaunch pricing
Live in 2–4 weeks
Unlimited documents, synced live
See pricing
Where it can help
  • Internal assistant for HR, IT, or legal questions over company handbooks
  • Technical questions over 1000+ pages of product documentation
  • Semantic search across your whole email, Slack, and ticket history
  • Compliance Q&A with exact pointers to the relevant legal article
Questions you can try
"what AI services do you offer?""How does a project with you go, step by step?""do you only work with clients in Romania?"
Productivity

An AI agent vs. hiring someone for the same work

The agent isn't a replacement for people. It takes the repetitive work off their plate, so your team handles what actually needs judgment. Here's what that looks like in numbers.

Hiring for the role

This AI agent

Monthly cost≈ €2,000+ (salary plus employer taxes)from €119/month, all-in
Availability8h/day, 5 days a week24/7, weekends and holidays included
Response timeMinutes to hours, one customer at a timeInstant, even with hundreds of conversations at once
Time to productive1–3 months of recruiting and onboardingLive in 1–4 weeks, trained on your content
Vacations & turnoverVacations, sick days, resignations, retrainingNone. It just keeps learning from real conversations.
≈ 6% of the monthly cost of an employeeSee pricing

Rough estimate for an average EU support or sales role, gross salary plus employer taxes. The agent works alongside your team, not instead of it.

Pricing

Pick a starting point

Launch pricing while we grow. Setup and brand-voice tuning are included, and we keep optimizing after launch. Models run privately in the EU. No per-message fees, no long-term contract.

Starter

€119/month

one-time setup €590

  • Indexes up to 500 documents
  • Every answer cites its source
  • Julien's Model: your data never leaves the dedicated server
  • Knowledge base refreshed weekly
  • A search widget for your intranet or site
Delivery: Live in 1–2 weeks

Professional

Most popular
€229/month

one-time setup €1190

  • Everything in Starter
  • Unlimited documents, synced live
  • Connectors for SharePoint, Drive, Confluence, and Notion
  • Julien's Model for everyday questions, Claude for the complex ones
  • Permissions by role and by department
  • Analytics on what your team actually asks
Delivery: Live in 2–4 weeks

Enterprise

Custom quote

Setup included in the quote

  • Hosted on-premise or on a dedicated EU server
  • SSO and full audit logging
  • Ingestion pipelines built for your sources
  • A dedicated SLA and priority support
Delivery: We plan the rollout together

Julien's Model

Any plan can run on Julien's Model, the AI we host ourselves on a dedicated server in the EU. Nothing leaves that server: no outside APIs, and we never train on your data.

Dedicated EU serverNo external APIsGDPR by design
Common questions

The questions we hear most

Straight answers on how we set each agent up inside your business.

How many documents can you index?

On Professional, up to 500 documents or 2 GB of text. Enterprise has no practical limit; we've shipped systems with over 50,000 documents and sub-second search.

What happens when I update the documentation?

The system stays connected to the source (Notion, Drive, SharePoint, Confluence, Git) and re-indexes on its own. Changes show up in answers within minutes, not days.

How do you make sure it doesn't hallucinate?

Two things. One: if the retrieved documents aren't relevant enough, the system says it doesn't know instead of improvising. Two: every answer cites the source document so you can check it yourself. For sensitive work, legal or medical, we also put a human in the loop for high-stakes answers.