Technical leadership
Research & development
Turin, Italy
Software development and technical leadership
Engineering Team Lead
I help the team
make technical
decisions.
Goals and constraints give people a common reference.
Matteo VincentiEngineering Team Lead, On Page®
I set the technical direction and share the context the team needs to make decisions independently.
See how I workMy background
From writing software to leading a team.
I explain
the reasons
behind decisions.
I write code, and at On Page® I also work on architecture, technical direction and research. I want the reasoning behind a decision to make sense to the person who has to revisit it a few months later.
I share constraints and discuss trade-offs with the team so we can assess proposals, including alternatives to my own.
software development
I work on code and architecture.
My work now also includes leading the team.
Discussion within the team
I discuss proposals
with the team.
When discussing a decision, I want to understand the reasoning behind each proposal and consider approaches different from the one I had in mind.
Each proposal starts from different reasoning.
Connect the proposals to the shared criteria.
From proposals to a decision / Illustrative example
Decisions within the team
How I approach
engineering decisions.
These examples show where I would start when the team needs to make a decision.
Pick a situation ↓
Examples of team decisions
Trust and responsibility
Assessing alternatives with the team.
When the reasoning behind a decision lives in one person’s head, the whole team depends on that person. I prefer to share the goals and constraints, hear people’s ideas and make it clear who can decide what.
- Understand the goals
- Discuss the options
- Give people ownership
Everyone involved should know who is responsible for each decision.
Public projects
My projects
on GitHub.
/01TypeScript / Logging
LogService
A TypeScript library for organising application logging.
Configurable strategies and providers for application logging.
Explore the repository ↗/02Docker / Observability
Pi System Monitor
Keep an eye on a Raspberry Pi, with metrics and notifications.
Metrics, notifications and container management for Raspberry Pi.
Explore the repository ↗React & Next.js / TypeScript / Node.js & PHP / Docker & AWS
What I’m working on now
I design agents
and MCP integrations.
I design agents and the MCP servers that connect them to software: what data they can read, which operations they can request and with whose permissions. I work on the code, the workflows and context retrieval with RAG.
I start with what the application actually does. Then I decide which operations to expose to agents, what constraints they need and where someone must confirm a change.
Step / 01
Retrieve the product documents.
The example starts with a request: fill in the missing descriptions for a set of products. I retrieve relevant specifications and documents, with references. RAG gives the model those sources as context; it doesn’t guarantee that they are complete or correct.
- Input
- A request to complete descriptions, plus product documentation.
- Output
- Useful specifications and passages, with source references.
request = readRequest()retrieved = search(productDocs, request)context = selectRelevant(retrieved)sources = attachReferences(context)What needs checking
Flag missing data without filling it in.
Step 1: Retrieve the product documents.
Illustrative workflow. No model is running. This is a general example, not On Page®’s architecture.
A project at On Page®
On Page® / MCP
Connecting the PIM
to AI assistants.
At On Page®, I worked on the MCP integration that lets AI assistants read and update PIM data using the user’s permissions.
Read the article · in ItalianMatteo Vincenti ·
From a request to product data«Which product records have missing data?»Follow the requestClose the walkthrough
01 / The assistant
AI
Interprets the request and selects a tool.
02 / The connection
MCP
The MCP (Model Context Protocol) server exposes the PIM’s tools.
03 / The software
On Page®
On Page® returns the data the user can access.
Illustrative example. Not connected to the PIM.
Read
Product records and attributes to compare or complete.
Request changes
Product data updates, including descriptions and translations, across multiple products.
The user’s permissions still apply. Sensitive operations require confirmation.
Blog
Latest
from the blog.
AI
Prepare a project for Claude Code and Codex: from setup to the first change
From an empty folder to a verified first change: AGENTS.md and CLAUDE.md instructions, tests, permissions and a handoff for coding agents.
AI
“Act as an expert”: what a role prompt changes
What does a role add to a prompt? Compare persona, message roles and explicit criteria with four complete prompts for the same caching decision.
Performance
UUIDv7 or bigint in PostgreSQL: arrival order matters too
A Docker comparison of bigint, UUIDv4 and UUIDv7: insert time, index size, WAL and arrival order. Includes measured results and runnable code.
Who is Matteo Vincenti?
I'm an Engineering Team Lead at On Page® in Turin, Italy. I started in software development; today my work also includes technical leadership, architecture, and research and development.
What do you do at On Page®?
I work on the technical decisions behind the product and on testing new ideas. I assess how a system can evolve and what work the team will need to maintain and change it.
What does leading an engineering team mean to you?
Making the goals clear and explaining the reasons behind decisions. I want people to have the context they need to decide, challenge ideas, and bring their expertise to the work.
What is your current work on software agents and AI integrations?
I design software agents, MCP (Model Context Protocol) servers, and integrations that let AI use the data and features of existing applications. I also work on workflow orchestration and RAG (retrieval-augmented generation). I continue to write code.
Where can I find something you've built or written?
On GitHub you'll find LogService, a TypeScript logging library, and Pi System Monitor, a set of tools for monitoring Raspberry Pi. On the On Page® blog I wrote about integrating AI, MCP, and PIM; the article was published on 2 August 2026 and is in Italian.
Contact
An engineering decision, a team question, or connecting agents to software: send me a message on LinkedIn.