AI Product & Behavior Designer

The space where product intent becomes model behavior.

I design AI agents that know when to act, ask, stop, and hand off. Then I build the prototype, write the evals, and turn product decisions into model behavior teams can test.

I started in language-model training and NLU, moved through production voice and chat assistants, then into LLM and agentic systems. My edge is translating messy customer problems into behaviors an AI system can execute, evaluate, and safely hand off.

Where
Intuit · Credit Karma · Sam’s Club · Apple Siri · Meta
View selected work
Portrait of Simone Muro
Selected work

Six cases. One open to read, the rest on request.

Ask my agent about any of them. For a full case study, send the prefilled request and I’ll reply from my own inbox.

Intuit Intelligence · Billing skill
Every charge,
explained.
grounded in the customer’s own data
personalized responses explainability first
Featured · Agentic era · By request

“What is this charge?” is the most common billing question, and the hardest to answer well.

A skill that grounds every answer in the customer’s own account: personalized, explainable, and honest enough to intercept a cancel before it happens.

✉︎ Request the full case
Intuit Intelligence · Payroll tax skill
what good looks like
personalized, jurisdiction by jurisdiction
Payroll tax skill · Agentic era · By request

Payroll tax guidance lived in a few experts’ heads. That doesn’t scale.

So define what a good diagnosis looks like, personalize it jurisdiction by jurisdiction, and grade the live skill against it.

✉︎ Request the full case
QuickBooks Voice Assistant
+3.9pt
containment lift, shipped
Voice · LLM era · By request

On a phone line, there’s no screen to fall back on.

Every word is the interface: what the model can say in seconds, when to clarify, when to hand off. Shipped a +3.9pt containment lift.

✉︎ Request the full case
Vapi prototype · Voice troubleshooting
fixed on the call
a live walkthrough, end to end
Voice troubleshooting POC · LLM era, 2024 · By request

Self-help sends the answer. This prototype stayed until it was fixed.

System instructions, grounded product content, and a live voice loop, with a recorded session that shows the model clarify, pace itself, admit a limit, and recover.

✉︎ Request the full case
Intuit · Cancellation saves
96.6%
routing precision, in evaluation
Cancellation saves · LLM era · By request

Not everyone who clicks “cancel” actually wants to leave.

A classifier accurate enough to route the truly savable to a specialist, and give everyone else a clean goodbye.

✉︎ Request the full case

Handoff

If your team is deciding how an agent should behave, I can help.

simonermuro@gmail.com LinkedIn Request resume

About the artifacts and how this site was made: colophon.