Available for new projects · Remote · Milan, Italy
Trusted by teams at H-Farm, GB Viaggi, Pellemoda, and more · GDPR & EU AI Act–ready.
Live trace of a production agent run: routing, retrieval, GDPR guardrails, actions, and LangSmith observability.
RevAgent
Visit →Autonomous RevOps platform for B2B SaaS — 7 LangGraph agents that score deal health, forecast revenue, draft follow-ups, and escalate at-risk deals with human-in-the-loop safety.
BandiFinder AI
Visit →Autonomous AI agent system that crawls EU/Italian procurement portals, parses tender documents, matches company profiles using LangGraph multi-agent orchestration, and triggers real-time alerts. Firestore + Next.js dashboard.
More in the case studies.
“The automation handles thousands of operations daily without manual work. It completely changed how we operate.”
See the code
langgraph-starter-kit →My open-source, production-ready multi-agent starter kit for LangGraph — 7 patterns, 5 LLM providers, MCP integration, and an HTTP server with SSE streaming. This is how I build.
The lowest-risk start is a Production-Readiness Audit (€1,500, one week — credited if we continue). Most clients then run a fixed-scope Sprint (€8,000, 2–4 weeks) and graduate to a Build for the full production system. See services & pricing or get a tailored figure with the cost calculator.
A fixed-scope Sprint (a working agent in 2–4 weeks) starts at €8,000; a full production system runs €18,000–€35,000. You can get a tailored estimate with the AI Agent Cost Calculator, or book a free call for a real quote.
A demoable agent ships in 2–4 weeks (Sprint). A full production system with multi-tenancy, billing, and observability runs 6–10 weeks (Build). You get a live demo every Friday.
Yes — I work remotely with startups and SMBs across the EU and English-speaking markets, in English or Italian, async-first.
For anything beyond a single prompt, I default to LangGraph: it gives you an explicit state machine, durable execution (checkpointers), and first-class human-in-the-loop — the things you need to run agents reliably in production. LangChain is great for the building blocks; CrewAI is quicker for simple role-based crews but harder to control at scale.
That's the most common ask. I add durable execution, evaluation sets, LangSmith observability, guardrails, and the auth/billing/multi-tenancy around it — so a notebook demo becomes a system real users can depend on.
100%, from day one. No lock-in, no proprietary black boxes; Builds include handover documentation.
Book a free 30-minute call — tell me what you're building and I'll tell you if I can help and what it would take.
Not ready? Get my AI-agent build checklist + occasional notes.