You will get AI Customer Support Agent | Support Chatbot | Helpdesk Ticket Triage
Project details
Most RAG demos work on five clean PDFs and fall apart on a real corpus. The failure is rarely the model. It is chunking that splits a table down the middle, retrieval that returns the confidently wrong passage, and no way to tell the difference until a user complains.
I build retrieval that survives real documents. Ingestion that handles your actual formats, chunking tuned to how your content is structured, embeddings and hybrid search over pgvector, and reranking where it earns its latency.
The part most people skip: evaluation. You get a question set drawn from your own material and a measured score, so "is it working" stops being a matter of opinion. When grounding fails, you will know which question failed and why.
Deployed on your infrastructure, not handed over as a notebook. Docker, migrations, and the operational pieces that keep it running after I leave: caching, spend ceilings, observability.
Built on production experience: a cognitive platform with a memory graph and retrieval over a live corpus, delivered across fifteen approved milestones.
Written and asynchronous throughout. A plan before code, staging before production, measured numbers instead of adjectives.
I build retrieval that survives real documents. Ingestion that handles your actual formats, chunking tuned to how your content is structured, embeddings and hybrid search over pgvector, and reranking where it earns its latency.
The part most people skip: evaluation. You get a question set drawn from your own material and a measured score, so "is it working" stops being a matter of opinion. When grounding fails, you will know which question failed and why.
Deployed on your infrastructure, not handed over as a notebook. Docker, migrations, and the operational pieces that keep it running after I leave: caching, spend ceilings, observability.
Built on production experience: a cognitive platform with a memory graph and retrieval over a live corpus, delivered across fifteen approved milestones.
Written and asynchronous throughout. A plan before code, staging before production, measured numbers instead of adjectives.
AI Algorithms
Large Language Model, Transformer ModelAI Applications
Natural Language UnderstandingAI Development Language
PythonAI Tools
Azure OpenAI, Hugging Face, Word2vecAI Models
BERT, ChatGPT, GPT-4What's included
| Service Tiers |
Starter
$399
|
Standard
$1,800
|
Advanced
$3,500
|
|---|---|---|---|
| Delivery Time | 4 days | 10 days | 16 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 | - | - |
About Guglielmo
AI Agents, Chatbots & Workflow Automation | Production AI Engineer
Milan, Italy - 2:02 pm local time
I build AI agents, chatbots and automations that run in production: connected to your real data, wired into the tools your team already uses, and still standing after the first thousand messages.
WHAT I BUILD
• AI agents that actually do the work. Multi-step reasoning, tool calling, and the guardrails that stop them going off-script or running up your bill.
• Chatbots that answer from your own documents, with the source attached to every answer and an honest "I don't know" instead of an invented one.
• Workflow automation, n8n or custom, that removes the task nobody on your team wants to do twice.
• AI built into the app you already have, rather than a separate toy nobody opens.
WHY CLIENTS KEEP COMMISSIONING
I ship on rails. A written plan before I touch code. Staging before production. Numbers you can verify instead of adjectives. I name my own bugs before you find them, and I will tell you when a feature is not worth building, which costs me money and saves you more.
My last client commissioned continuously for five months and wrote this: "one of the most substantive technical collaborations of my career."
HOW I WORK
Fully asynchronous, entirely in writing. No calls, no standups, no scheduling across time zones. You get updates you can read at 2am and forward to your team, and every decision stays on the record instead of evaporating in a meeting.
Stack: Python, FastAPI, Next.js, PostgreSQL, pgvector, Docker, OpenAI and Anthropic APIs, Stripe. MIT Professional Education certificate in Large Language Models. Background in security, which mostly shows up as systems that fail closed instead of loudly.
Tell me the outcome you need and what is currently in the way. You get back a scoped plan with a fixed price, usually same day.
Steps for completing your project
After purchasing the project, send requirements so Guglielmo can start the project.
Delivery time starts when Guglielmo receives requirements from you.
Guglielmo works on your project following the steps below.
Revisions may occur after the delivery date.
Index your corpus and prove retrieval works
I ingest your documents, chunk and embed them, and stand up hybrid search. Before any generation is wired in, you get retrieval results for your own questions, so you can see what the system finds before it starts writing sentences.