# Felipe Casadei

> Felipe Casadei leads mixed methods UX research at AWS, connecting behavioral science, AI evaluation, product strategy, and working prototypes.

Mixed Methods UX Research & AI Evaluation

Studying people to shape and evaluate AI behavior

Research goes beyond job descriptions. I take a player-coach approach, combining technical skills with research experience.

Also published as Felipe Imbelissieri-Casadei. Based in Brooklyn, New York.

This is the concise profile. [Detailed background, evidence, and implementation notes](https://felipecasadei.ai/llms-full.txt).

## Selected UX work

- [Amazon Bio Discovery](https://felipecasadei.ai/research/amazon-bio-discovery): My research made scientific collaboration, learning, and inspectable AI central to Amazon Bio Discovery’s product direction. I led strategic and technical studies and built working prototypes that shaped shared workspaces, evidence controls, and architectural requirements, helping leadership commit resources to a broader scientific workbench.
- [Alexa for Shopping](https://felipecasadei.ai/research/alexa-for-shopping): Product comparisons grew from thousands to a reported 10 million per month within 90 days of the team’s redesign. I led the international mixed methods research that shaped conversational behavior, guided discovery, and comparison features.
- [Prime customer experience](https://felipecasadei.ai/research/prime-customer-experience): Prime teams gained a comparable view of customer experience across 22 countries, grounded in local membership value. I adapted the measurement framework and expanded quarterly surveys with conjoint analysis and contextual inquiry.
- [Voice interaction at Meta](https://felipecasadei.ai/research/voice-interaction-at-meta): Established motorcycle couriers as a business segment for WhatsApp and shifted success measures from message volume toward interaction quality. Through fieldwork in India, I connected communication patterns with the cognitive demands of working in motion, informing voice interaction, accessibility, and product positioning across languages and professional contexts.

Later Amazon customer and sales figures describe the product as a whole, not the causal impact of my research. The [detailed profile](https://felipecasadei.ai/llms-full.txt) links the original Amazon sources.

## Prototypes and research

- [Petra](https://felipecasadei.ai/projects/petra): Petra is an AI harness for science, built to make model-generated claims traceable to their evidence. I’m developing a workbench that connects hypotheses to supporting and conflicting source passages, with people reviewing changes before they enter the trusted record. Status: In development.
- [Amazon Resonance](https://felipecasadei.ai/projects/resonance): Amazon Resonance brings survey authoring and source analysis into one research workspace. I designed and coded it so researchers can turn a document of questions into a live survey and continue analysis while code, documents, and audio ingest in the background. Status: In testing at AWS.
- [Felicity](https://felipecasadei.ai/projects/felicity): Felicity’s writing skills help AI assistants revise prose while preserving the author’s meaning. I built separate Review and Write skills, drawing on pragmatics to examine evidence, relevance, common ground, and the force of a statement. Status: Available on GitHub.
- [Face Lab](https://felipecasadei.ai/#face-lab): An active Raspberry Pi prototype for on-device facial analysis, with an interface for experiments on prosody and expression.
- [Graph Theory: From Zero to Diestel](https://graphtheory.felipecasadei.ai/): An independent sixteen-chapter teaching companion to Reinhard Diestel’s Graph Theory, with visual explanations, quizzes, and a Königsberg bridges game.
- Prenatal Prosody Perception: An experiment in design on learning from the rhythm and melody of muffled speech.

## Education

BA in Philosophy, University of São Paulo; MS in Neuroscience, Columbia University; fMRI research fellowship at the Martinos Center, Harvard Medical School. MS in Computational Linguistics in progress at the University of Washington.

## Profiles and access

- [LinkedIn](https://www.linkedin.com/in/fecasadei)
- [GitHub](https://github.com/beethovensaves)
- [Medium](https://medium.com/@felipe_cas)
- [dratsi-pod on Spotify](https://open.spotify.com/show/7cH9c1aV3hg2jVIKEqUIWB): Book and paper summaries.
- [Full portfolio](https://felipecasadei.ai/portfolio): Password protected.
- Contact: felipe@dratsi.com