SEO7.ES — Web, SEO, AI & Automation
Skip to content

Case · AI assistant

Three models, 100+ operations, all on the owner’s server.

🤖

3 AIs in one bot

⚙️

Routine automation

💬

Runs right in Telegram

🧩

Decision support 24/7

One bot, three models: request routing, context memory, a knowledge base (RAG), routine automation and local deployment for privacy.

A personal AI assistant in Telegram combining GPT, Claude and Gemini. It automates routine tasks, remembers context and supports decision-making — with local deployment for data privacy.

Personal AI assistant

AI Assistant

Want a similar project?

Take a short brief — we’ll come back with a plan and a quote.

An assistant in Python that decides for itself which language model gets each task: GPT, Claude or Gemini. It reads documents, walks into servers over SSH, edits spreadsheets, drives a browser and runs shell commands. It is controlled from a web interface or straight from Telegram, and the whole system is deployed on the client’s own infrastructure, so the data goes nowhere.

Client: private individual · Platform: Telegram and a web interface · Category: AI assistant

The short version

  • More than 100 operations in one assistant, from text generation to server monitoring.
  • Three models instead of one: GPT, Claude and Gemini, picked for the task at hand.
  • Local deployment on the client’s infrastructure: data and processes stay under their control.
  • Two control channels: a web interface for complex work and Telegram for anywhere else.
  • Its own character and logic, tuned to the client’s workflows and way of speaking.
  • Access to real working tools: SSH, the file system, Google Sheets, a browser, PDF processing.

Tech stack

  • Language: Python.
  • Models: GPT, Claude and Gemini with dynamic selection based on the task.
  • Deployment: local, on the client’s infrastructure.
  • Interfaces: a web interface and a Telegram integration.
  • Integrations: external APIs, SSH, Google Sheets, a web browser, the file system.

Different models are strong at different things: one holds a long context better, another is more precise with code, a third is faster and cheaper on simple queries. So the assistant is not tied to one vendor and picks the executor per task.

How it started

An ordinary chat with a neural network solves half the problem. It suggests the command but does not run it; it writes the text but does not put it in the right file; it explains how to check a server but never goes there.

The client needed a doer rather than a conversationalist: one message in Telegram should end in a real action on their machines and in their documents.

The second requirement was tougher than the first. Working files, server credentials and internal data all pass through the assistant, so a cloud build was out of the question. The system was deployed locally, on the client’s infrastructure, where they control both the processes and the storage.

Full list of what was built

🧠 Intelligence and language models

  • GPT, Claude and Gemini combined with dynamic model selection
  • The assistant’s own logic and character, tuned to one specific person
  • Advanced search, content generation, data analysis
  • Image generation

⚙️ Automation and system operations

  • Shell command execution
  • File management
  • Web browser automation
  • PDF processing
  • Server monitoring over SSH
  • Working with Google Sheets

💬 Access channels

  • A full web interface for complex operations
  • A Telegram integration: control from anywhere in the world

🛡 Security

  • Local deployment on the client’s infrastructure
  • Full control over processes and data

Results

MetricValue
Operations in the assistantmore than 100
Language models3, chosen per task
Control channels2: web and Telegram
Where it runsthe client’s infrastructure
Data in external servicesnone stored
Working integrationsSSH, files, Google Sheets, browser, PDF

Not sure where to start?

We’ll review your case in a free consultation and propose a solution.

Itemised estimate

10 itemsTimeline: ~1 month
À la carte (separately)€1900
Bundle saving−€1300
Turnkey package€600

Prices per our list. Each module costs more separately: integrations, management, overhead. As one project on a single backend it’s cheaper. Exact quote for your case after the brief.

The more features, the better the bundle

SeparatelyBundle price
Минимум · €390Стандарт · €1490€1900−€1300This project€600Scope of features →10Cost, €

Bought separately, cost grows linearly. As a bundle it plateaus: shared architecture, one backend, code reuse. So the more features, the wider the gap — and the bigger your saving. This project (41 features) is already at the plateau.

Frequently asked questions

It answers using GPT, Claude and Gemini, remembers context, keeps a knowledge base, automates routine tasks and supports decision-making.

Related projects.

Ready for your project?

Leave a request — we’ll estimate the timeline and price for your business.