4 Aug 2026 · 5 min read
Drop the Bloat
Everything you hand a coding agent, it has to carry. Mine was hauling 35K tokens of instructions before I typed a word. A field note on cutting that to 13K, and on knowing when context stops earning its place.
Lorenzo Germini
AI Product Engineer · Cuneo, Italy, CET
CV →
I build AI products end-to-end and write about what actually works.
Right now that's the AI engine behind Complaion, a compliance platform for ISO certifications: LLM agents doing real compliance work in the background, and the evals that show when they can't be trusted. Before that: pharma manufacturing, digital health, and a GenAI startup.
Start with the writing ↓Writing
Field notes, mostly from building with AI, published on germinai. No definitive guides. Things I tried, what broke, and what earned its place.
About
I'm an AI product engineer: I ship AI products end-to-end, from the models and infrastructure to the interface people actually touch, and stay on the hook for whether the thing helps anyone. Full stack in the literal sense: backend, frontend, and the product calls in between.
These days that's the AI engine behind Complaion, a compliance platform for European SMEs getting and keeping ISO certifications. The interesting problem is making the agents in the background reliable enough to trust with real compliance work, and knowing when they're not. Before that: AI for pharma manufacturing at GSK, AI R&D in digital health, and a GenAI EdTech startup I built as founding engineer. The through-line hasn't changed. Technical depth only matters when it meets a real user problem.
Outside work: sports, side projects, and rabbit holes on tech entrepreneurship and biohacking.
Work
May 2025 – Present
AI Product Engineer · Complaion
Building the agentic AI core of the product: agents and automation workflows that combine business context with expert feedback, backed by evaluations that track reliability in production. Shaping product decisions with business stakeholders and shipping AI features end-to-end, from problem definition to production, across AI, backend, and frontend.
Nov 2024 – Apr 2025
Founding AI Engineer · Stealth GenAI Startup
Backend and GenAI API layer from zero on AWS. A RAG stack with custom parsing for handwritten input, plus the tracing and evals to tune retrieval.
Sep 2023 – Oct 2024
AI Engineer · GSK
Time-series forecasting and anomaly detection on plant sensor data, semantic NLP for fault detection, and a water-rejection strategy projected at 10,000 m³/year.
2021 – 2023
- A Stable Diffusion interior-design MVP, killed on the evidence
- Biomedical-literature summarisation at Burgeon Labs
- Fill-parameter ML at Roche
- EPFL MSc, Life Sciences Engineering
Projects
Quadrell
My independent studio, building websites and workflow automations for small businesses and independent professionals. I handle each project from the initial brief to launch, and build around how the business already works.
Independent Studio
Websites
Automations
L'Oracolo della Ghigliottina
An archived AI game companion for La Ghigliottina, the final round of the Rai 1 quiz show L'Eredità. It found the word connecting five clues, submitted as text or as a photo of the TV, and handled rate limits. The service is closed. Past results are still available to browse.
Side Project
Archived
Generative AI
Next.js
Vercel AI SDK
Telegram Bot
WhatsApp Bot
Systems
agent systems · eval harnesses & tracing · end-to-end shipping, coding agents in the loop