You will get one production-ready AI agent running inside your own stack
Project details
Most teams have one process that eats hours every week and never quite justifies a hire. That is what this project automates.
You get one agent running inside your own stack, with its skills, tools and prompt setup versioned in your repo. It uses your systems, follows the rules we agreed, and hands anything uncertain back to a human.
I have built agentic tooling and MCP integrations in production, on top of ten years running systems that carry real traffic. So the agent ships with guardrails, failure handling and a runbook, not just a clever prompt.
The point is that you can build the next one without me. The enablement session is your team shipping a change to the agent while I watch, so the knowledge stays in the building.
Scope and price agreed in writing before I start. Based in Vienna, working across EU hours, in English, German or Italian.
You get one agent running inside your own stack, with its skills, tools and prompt setup versioned in your repo. It uses your systems, follows the rules we agreed, and hands anything uncertain back to a human.
I have built agentic tooling and MCP integrations in production, on top of ten years running systems that carry real traffic. So the agent ships with guardrails, failure handling and a runbook, not just a clever prompt.
The point is that you can build the next one without me. The enablement session is your team shipping a change to the agent while I watch, so the knowledge stays in the building.
Scope and price agreed in writing before I start. Based in Vienna, working across EU hours, in English, German or Italian.
AI Algorithms
Large Language Model, Multimodal Large Language ModelAI Applications
AI-Generated Code, AIOps, Natural Language Generation, Natural Language UnderstandingAI Development Language
PythonAI Models
ChatGPT, GPT-4, OpenAI CodexWhat's included
| Service Tiers |
Starter
$1,200
|
Standard
$2,200
|
Advanced
$3,400
|
|---|---|---|---|
| Delivery Time | 10 days | 21 days | 35 days |
Number of Revisions | 1 | 2 | 3 |
AI Model Integration | - | - | - |
Batch Normalization | - | - | - |
Database Integration | - | - | |
Detailed Code Comments | - | ||
Image Upscaling | - | - | - |
MLOps | - | - | |
Model Deployment | - | ||
Model Documentation | - | ||
Model Monitoring | - | - | |
Model Testing & Optimization | - | - | - |
Model Tuning | - | - | - |
Natural Language Processing | - | - | - |
NLP Tokenization | - | - | - |
Pre-Training | - | - | - |
Prompt Engineering | |||
Setup File | - | - | - |
Source Code |
Frequently asked questions
About Federico
Senior AI & Cloud Engineer | Voice Agents, Agentic AI, AWS, Next.js
Vienna, Austria - 9:49 am local time
What I deliver:
- AI voice agents. Speech-to-text and text-to-speech pipelines, latency tuned, deployed on a working demo URL.
- Agentic AI and automation. One production-ready agent inside your own stack, with custom tools and prompts versioned in your repo, plus a runbook so your team can extend it.
- AWS architecture. Serverless, event-driven design, and independent reviews of infrastructure you already run, covering cost, reliability, security and scale.
- Next.js websites. Fast, fully indexed, and yours outright.
Track record: five years at ImmobilienScout24 working across 60+ microservices on AWS under high-traffic production load, and CTO-level work for European startups in fintech, AI and streaming. xcore.gg and Picks & Bans are my own products, taken from an idea to live users.
Scope and price agreed in writing before we start. Based in Vienna, working across EU hours, in English, German and Italian.
Tell me the outcome you need and I will tell you exactly what it takes to get there.
Steps for completing your project
After purchasing the project, send requirements so Federico can start the project.
Delivery time starts when Federico receives requirements from you.
Federico works on your project following the steps below.
Revisions may occur after the delivery date.
Scope the agent
We pick one task worth automating and agree what the agent is allowed to do on its own and what stays with a human.
Build it inside your stack
The agent, its custom skills and tools, and the prompt setup, all versioned in your own repo so nothing lives on my machine.