Project
Sanitas Hospitals: Alexa in the patient room
Conversation and multimodal design, prototype and rollout of Alexa in the rooms of the Hospital Blua Sanitas Valdebebas.
“Our agent answers, but it can't hold a conversation. It sounds like a machine, not like our brand.”
Services
Conversational agents, designed and built
Technology works the way you expect when the conversation is well designed and well built. We do both for assistants, chatbots and LLM-based agents: we decide what they can do, how they express themselves, how they recover when they don't understand and when to hand over to a person, and we build them connected to your data and systems.
Conversation design and development for chatbots and AI agents
Conversation design decides what an assistant, chatbot or AI agent can do, how it speaks, how it recovers when it doesn't understand and when it hands over to a person. We've practiced it since 2017, with classic assistants and with language models; in 2019 we were a featured Amazon Alexa agency in Spain.
Strategy and use cases
We decide where a conversation adds value, and where it doesn't.
Personality and tone
We define the assistant's personality and how it speaks in voice and text, consistent with your brand.
Dialogue design
Flows, instructions for language models, error handling and handover to people.
Multimodal experiences
Assistants and agents that combine voice, text, images and screens, across phone, web, apps and devices.
Evaluation
We analyze how your chatbot, voice assistant or agent performs, and propose improvements.
Development and integration
We choose platforms and models for the task, the budget and the language, and build the agent connected to your data and systems, on our own or with your engineering team.
How we work
01
Explore
We understand the challenge and review what today's technology can do for your case, your language and your data.
02
Prototype
We build just enough to validate the idea with real people.
03
Pilot
We try it out in your organization, measure and adjust.
04
Hand over
We document and train your team so they can keep evolving it.
What you get
- Personality and tone guide
- Conversation design and instructions
- A working assistant or agent, tested with users
- Evaluation and improvement recommendations from real usage
Who it's for
- Tech and product teams building assistants or agents
- Design teams that want to improve their assistant
- Brands that want their own conversational channel
- Media and publishers with interactive experiences
Related projects
Project
Sanitas Mayores: Alexa in care homes
We supported Sanitas Mayores as Alexa arrived in its care homes: use cases, conversation design for older people and integration with its AI, SanIA.
Project
Evaluation and personality for a real estate portal's chatbots
Evaluating a real estate portal's two help chatbots, and a workshop to define their personality.
Project
A synthetic voice of its own for an energy company
Designing and creating an exclusive synthetic voice for a major energy company's advertising, available in Fonos.
Project
Clevergy: conversation design review
We reviewed the voice assistant of Clevergy, a platform that helps people understand their home electricity use, and proposed conversation design improvements.
Project
A voice assistant for home energy use
Conversation design to bring the features of a home energy app to a voice assistant: personality, conversations, sound design and integration.
Project
Alexa, open Pasapalabra
Play Pasapalabra, the Antena 3 TV game show hosted by Roberto Leal, as if you were a contestant.
Project
Live translation for emergency services
A face-to-face translation mobile app so emergency medical staff can talk to patients who don't speak Spanish, without storing their voice.
Conversational agent design and development FAQ
Do you only design them, or build them too?
Both. We can handle the full build or work alongside your engineering team, who know your systems and keep what they learn.
Do you work with generative AI or only classic assistants?
Both. We've been designing and building conversations since 2017, before and after language models: the principles stay the same, the tools change.
What's your experience with voice assistants?
We were a featured Amazon Alexa agency in Spain and Nieves Ábalos was recognized as an Alexa Champion. We've built voice experiences with screens, such as Pasapalabra with Atresmedia, and for companies like Grupo Planeta, Lingokids and Mahou.
How long until an agent is up and running?
A proof of concept with real users can be ready in weeks; a production agent connected to your systems depends on the integrations and how many tasks it handles.
What do we need to have ready?
A clear idea of what it should solve and for whom, access to the information it needs (documents, databases, systems), and someone on your team who knows the process and how it fits into your systems. If you already have an assistant, its real conversations are the best starting point.
What can't a language-model agent do well?
It can confidently make up (hallucinate) answers, lose the thread in long conversations or drift from your brand's tone. We design it to know when not to answer, when to ask for clarification and when to hand over to a person, and we evaluate it before launch.
Services
Applied AI research and prototypes
From an idea or a research project to a prototype real people can try.
Custom synthetic voices
Custom synthetic voices for brands and media, in Spanish, its accents and Spain's co-official languages.
Assistant and agent evaluation
We measure how your assistant talks: what it understands, where it gets lost and when it shouldn't answer.
Training
Conversation design, assistant personality, synthetic voice and conversational AI, taught by the people who build them.
Got a voice or conversation challenge?
Tell us what you want to achieve. If we're not the right team, we'll say so.