2+ years as an AI Prompt Engineer & Research Lead at Airia
Earlier experience collaborating on NLP-focused aviation related applications, sparking my passion for AI
Certification in AI Prompt Engineering (Vanderbilt University)
Bachelor’s in Media Communication and Master’s in Digital Marketing & Social Media
Fluent in English, Portuguese, and Spanish
Part of the founding journey of Airia, growing it from a niche healthcare app to a full AI orchestration platform
I help people connect with AI in a way that feels natural, approachable, and genuinely helpful.
About me
Arii
AI doesn’t have to be a polite, boring assistant. Meet Arii—my fiery, funny AI persona designed to keep users on track with their health goals.
Large language models are inherently polite… but sometimes, being helpful means being a little bold.
In Arii’s design, I gave her 'permission' to speak strongly when a user’s choices went against their goals.
During testing, I asked if my husband having a hotdog with a beer was okay for his health plan. Arii’s response?
“Step away from the hotdog and beer.”
We all laughed—and learned that personality can make AI advice not only effective, but unforgettable.
Bringing AI Personas to Life
– Arii's Story
Education
Prompt design isn't just technical - it's personal.
As both a parent and a prompt engineer, I had a unique lens when developing the prompt libraries for BrainFreeze, Airia’s education platform. I wasn’t just researching how AI should respond—I was imagining how I’d want it to talk to my own child.
Built prompts that powered multilingual AI tutors and assistant personas, tailored to the learning needs of students, teachers, and even parents.
Led early research that shaped the platform's voice—balancing encouragement, clarity, and adaptability across languages and grade levels.
Designed conversational flows for tutoring, study planning, and behavior support across diverse learning scenarios.
Combined real-world parental instincts with prompt iteration and AI testing across multiple models.
Legal
In legal work, clarity matters more than creativity.
Working with in-house attorneys and feedback from real legal clients, I created the prompt libraries for Airia’s Legal AI Assistant, focused on compliance, consistency, and real-world usage.
Collaborated directly with two lawyers to understand tone, terminology, and boundaries in legal AI communication.
Created modular prompt templates for contract drafting, clause explanation, risk analysis, and citation support—all designed with auditability and safety in mind.
Focused on language that avoids hallucination and preserves intent—because in legal work, vague AI can be risky AI.
Took complex concepts and translated them into repeatable, controllable prompt flows for safe internal and external use.
Prompt Module
Context
In mid-2024, our team explored available prompt engineering tools (PromptMetheus, PromptKnit, PromptLayer, OpenAI Playground, Anthropic Console, etc.). We found a clear gap:
Tools were too technical for non-developers.
Limited ability to handle multi-turn conversations, collaboration, and ongoing testing.
No solution for version tracking or prompt lifecycle management.
Goal
Design an internal tool (initially called Workbench) to:
Enable team collaboration on prompt design and testing.
Provide version history and audit trails for traceability.
Support multi-model testing across providers (OpenAI, Anthropic,LLaMA, etc.).
Allow import of prior chats to evaluate prompt revisions in context.
Include real-world features missing from other tools, like variable support, function libraries, and file/photo inputs.
Outcome
This research shaped the Prompt Module. It offered a practical, user-friendly environment for testing, refining, and managing prompts at scale—something no off-the-shelf solution provided at the time.
Partnered with PR firms to help shape AI-assisted website copy, ensuring tone, brand alignment, and audience intent were baked into prompt design—not bolted on afterward.
Worked closely with cross-functional teams (product managers, legal advisors, engineers) to ensure AI assistants delivered accurate, compliant, and trustworthy responses.
Mentored and led interns on the prompt engineering team, guiding them through iterative prompt development and real-world testing methods.
Brought clarity and structure to complex AI projects, bridging the gap between non-technical stakeholders and technical build teams.
