Federico Caria

Experience Engineering

Knowledge shorts twice: Once in the tools. Once in the humans.

I build tools for complex knowledge and test whether they work. From user research through working code — end to end.

evaluate next
agent config idle
literature Exhaustive search across sources coverage
formalize Claims into testable form novelty
simulate Computational tests on real data evidence
dataset Build the corpus it needs evidence
rederive Independent path to the result corroboration
counter Steelman the rival model corroboration
stress Break it on edge cases review
review Adversarial verdict loop review
fingerprint what survived, what died, and why
The Lab

Most recent projects

Flowws MCP
live Internal product 2025-present

Flowws MCP

A computable UX knowledge system — HCI research encoded as a graph with every citation verified against its source, exposed to Claude Code through an MCP server so evidence lands in a developer's context window exactly when they need it.

Python Django Neo4j Pydantic MCP Qwen (HF Inference) +3
Bookshelf
live Libreria Rotondi, Rome 2025-present

Bookshelf

Barcode to catalog in under 10 seconds. A metadata aggregation platform for independent bookshops — scan, enrich from five sources, publish to WooCommerce.

Python FastAPI SQLite Vanilla JS Jinja2 pyzbar +2
04
in_development Personal research 2025–present

Impossible Papers

Multi-agent research engine that takes an impossible hypothesis, stress-tests it against real academic literature, and produces papers that read like hard science.

Python LangGraph Ollama Semantic Scholar API OpenAlex API Flask +2
Background

One thread, many domains

The throughline has always been one thing: rigorous evaluation of how humans interact with complex information systems, and building better ones.

It started with classical philology — close reading as a contemplative discipline, sitting with a text until it reveals what it actually says rather than what you wanted it to say. My MA thesis traced the arc from Roberto Busa's Index Thomisticus to modern computational text analysis.

Then HCI research at Sapienza and Cologne, funded by a Marie Curie fellowship: are digital scholarly editions actually serving their users? (Usually not — scholars preferred the PDF.) Three papers, lectures from Berlin to Tokyo to Buenos Aires, a PhD formalizing evaluation frameworks for knowledge tools.

Then eight years at Baymard Institute — the same question applied at scale. 700+ usability heuristics. Fortune 500 checkout flows. Empirical proof, over and over, that the tools fail and the humans fail harder.

Impossible Papers is where it all converges: a system that attacks both failure modes simultaneously. The tooling problem (multi-agent pipeline, automated literature, adversarial review) and the human problem (the system is the furnace, not the alchemist — human judgment stays exactly where it belongs, and gets removed everywhere it breaks things).

2018 — present
Senior UX Researcher
Baymard Institute
2015 — 2017
Ph.D. Human-Computer Interaction
Universität zu Köln
2014 — 2017
Marie Skłodowska-Curie Fellow
European Commission
2014 — 2015
UX Researcher
Digilab, La Sapienza
3 papers
CHI, CSCW, Springer LNCS
First author
2024 — present
Impossible Papers
Multi-agent scientific discovery
About me
Collaborate

The interesting problems are ultradisciplinary.

If you're working on something where the knowledge infrastructure is the bottleneck — whether that's a research lab, a scientific competition, or a business drowning in its own data — I'd like to hear about it.

Get in touch