An NTT DATA bootcamp on conversational AI and prompt design. Over 8 sessions I learned to understand, design, build, test, measure and plan the strategy of a conversational agent. With what I learned, I designed a voice assistant that lets patients of a private clinic book their appointments, and presented it at the final Demo Day.
Lima, Peru
5 weeks
Individual project
NTT DATA bootcamp (Conversational AI & Prompt Design)
Conversation Designer

Present the solution in a 5-minute pitch at the Demo Day, in a clear, engaging and easy-to-follow way.
Design a decision tree with branches for when no appointment is available.
Design generative AI prompts with guardrails that prevent wrong medical diagnoses, backed by a knowledge base of the clinic.
Plan an A/B test to improve the conversion rate.
Each bootcamp session had a hands-on activity, and through them I built parts of the deliverables. At the end, I brought everything together into one proposal and looked for a creative way to present it in 5 minutes. The following sections explain how I built each deliverable.
I asked different people how they book medical appointments. I wanted to understand what information matters to them, which steps they follow and at what point they prefer to talk to a person.
I split the flow into scenarios (what the patient says), steps, required data and possible outcomes: appointment booked, patient on the waiting list or handoff to a person.
Following what we saw in class, I defined which parts of the flow use generative AI, such as understanding what the patient describes in their own words, and which are deterministic, such as checking availability or booking the appointment.
I started from the prompt created in a class activity, which guided me through questions. For the final delivery, I added what the tool's checklist marked as missing and refined it with help from ChatGPT.
Specialties, doctors by specialty, locations, prices and accepted insurance.
High, moderate and low urgency criteria, and a guide from symptom to specialty. They guide, but never diagnose.
Cancellations and rescheduling, the waiting list, booking requirements, lab results and when to hand over to a person.
Past appointments and saved preferences. Only consulted after verifying the patient's identity.
In class we learned how to compare a control with a variant before launching something new, and drafted a first test. With the feedback and my decision tree, I adapted the plan to the moment when there is no appointment on the requested date.
When there's no appointment, the agent only offers the next available date, which can be weeks away, and patients drop off or ask to talk to the front desk. If they can also join a waiting list for their preferred date, handoffs to a person should go down.
The existing digital channels may be insufficient for ambiguous requests, personal preferences, or lack of availability.
A sample conversation showing how the agent understands, guides and resolves.
Less load on the call center, empty slots recovered, and the A/B test results as evidence.

The Demo Day conversation sums up the proposal: an agent that understands natural language, never diagnoses, and resolves or hands over when it should. Faced with chest discomfort, it asks a single question, guides without diagnosing and looks for the earliest appointment. When there's no slot, it books a backup date and adds the patient to the waiting list instead of handing her over.
Voice agents will be used more and more, and the difference lies in how they're designed. Talking with other people about their experiences, I noticed that many reject voice agents because they've had bad experiences with bots that didn't understand them. If an agent is well designed, covers the different cases and has the knowledge needed to resolve people's questions, that perception can change. In healthcare, it also has to know what it must not do and when to hand the case over to a person.
The pitch slides I presented at the Demo Day (in Spanish).
View presentation →The full document with the decision tree, the prompt with guardrails, the knowledge base and the A/B testing plan (in Spanish).
View PDF →The certificate from NTT DATA's Conversational AI & Prompt Design bootcamp.
View certificate →For questions about this project or collaboration opportunities, feel free to reach out.
Contact Me →