Selected projects
AI architecture and system design for government, enterprise operations, and platforms used by people every day.
The thread across all of them: trust as a system property — earned in how the architecture is decided, how context is managed, and how the AI reaches the user, not added on top of a working model.
Eunoia Care — AI Assistant for Caregivers
2025–present · Healthtech · Personal project · System design · AI architecture · Functional prototype
Outcomes
Significant reduction in caregiver cognitive load
Patient medical information available in seconds
Longitudinal medical history built through use, not as a separate task
Families caring for a chronic patient live overwhelmed by fragmented medical information: lab tests, imaging, hospitalizations, instructions from different specialists. Forgetting and fragmentation are the main source of anxiety and care errors.
The problem
Designing an experience where a caregiver — often emotionally involved and without clinical training — could capture information without friction, in any format, and retrieve it when needed, in the format they need. Trust was the central design constraint: without it, the caregiver would never delegate to the system.
What I designed
The complete product architecture and a multi-agent system with distinct specialties (lab interpretation, longitudinal medical history, natural conversation), each with its own context, tone, and autonomy boundaries.
The caregiver captures information in any format — photo, text, audio — and the system converts it into a structured event. The AI responds with data, charts, or honestly signals when it doesn't have the information. I built a functional prototype with the agents running on the actual model, validating design decisions before implementation — especially each agent's boundaries and uncertainty handling in a medical context.
The design prioritized three axes: lowering capture friction, building trust through verification and honesty, and respecting the emotional weight of the context.
Outcomes
Significant reduction in caregiver cognitive load
Patient medical information available in seconds
Longitudinal medical history built through use, not as a separate task
Industrial B2B Support Tickets
November 2025–present · Conceptual piece · Industrial · AI agents · context engineering · Laravel · Vue
What the design demonstrates
Dual-agent architecture: separate identities for operator and technician, with structured context handoff
Explicit confidence levels in every suggestion, with traceable source
Human escalation patterns with no context loss
Conceptual piece modeling how a B2B SaaS startup building support infrastructure for industrial machinery manufacturers could add AI to its ticketing platform — beyond a chatbot.
The problem
The real bottleneck wasn't ticket volume. It was what happened inside each ticket: incomplete descriptions, back-and-forth clarifications, technicians starting from scratch every time. AI couldn't solve this with a single generic system — different roles needed different interactions, and each role's trust threshold for acting on AI suggestions was different.
What I designed
Two agent systems with distinct identities — one for the operator under pressure, another for the expert technician — connected by a structured context object. Each suggestion includes an explicit confidence level and its source, so users can decide how much to trust each output. The system knows when to escalate and transfers the complete context to the human, without loss.
What the design demonstrates
Dual-agent architecture: separate identities for operator and technician, with structured context handoff
Explicit confidence levels in every suggestion, with traceable source
Human escalation patterns with no context loss
TÜV NORD Argentina · Sistema Cóndor
2023–2025 · Enterprise platform · AI-assisted operations · Laravel · Vue
Outcomes
80% reduction in administrative load
Teams focused on higher-value work
100% of operations centralized in a single platform
TÜV NORD operated with manual processes spread across multiple tools. Generating a commercial proposal took days of manual work and there was no centralized visibility of certifications or audits.
The problem
Internal users with very different expertise levels interacting with intelligent automation. The system had to decide when to act on its own and when to request human validation — without frustrating experts or abandoning less technical users. Trust had to scale with expertise, not be uniform across roles.
What I designed
The AI generates pre-proposals but always presents them as editable drafts — a design pattern that preserves user control without losing automation efficiency. Assisted flows show what the system did and why, so users can validate with context. Validation rules are configured by role, not by generic permissions.
Outcomes
80% reduction in administrative load
Teams focused on higher-value work
100% of operations centralized in a single platform
Mi Caja · Government Platform
2019–2023 · Government platform · Laravel · Vue
Outcomes
70% reduction in processing times
Elimination of unnecessary in-person visits
100,000+ active users in production
Complete inter-institutional document traceability
Document and benefit management for retired personnel depended on in-person visits and manual coordination across agencies. Each process required physical travel, paperwork, and phone follow-up. Information didn't flow between areas, and no one had real visibility of each case.
The problem
Processes dependent on physical presence, manual coordination across agencies, and zero visibility of the real status of each case.
What I designed
A digital platform that centralizes processes and coordinates approval flows between agencies, with a web portal, mobile app, and complete inter-institutional workflow. Government-level security and traceability — the foundation I now build AI-native applications and platforms on top of.
Outcomes
70% reduction in processing times
Elimination of unnecessary in-person visits
100,000+ active users in production
Complete inter-institutional document traceability
Got operations you want to streamline with AI, or an AI-native idea you want to build?
Tell me what you're building and I'll respond within 24 hours.