15+ conversational AI systems across healthcare, finance, retail and education
Ran a small AI services practice end to end, from first call to production, for clients in eight countries.
The challenge
Clients in very different markets wanted assistants that worked in their own language and connected to their own systems, without the budget of a large agency.
What I did
- Owned client relationships, architecture decisions and delivery for every engagement.
- Designed Rasa-based and LangGraph multi-agent systems with LLM integrations, RAG and API orchestration.
- Built multilingual assistants, including a Spanish chatbot with custom sentiment analysis, a Lithuanian multilingual assistant, a German educational chatbot, and a travel agent.
- Deployed on Docker, Kubernetes and the major clouds, with the client's team able to run it afterwards.
Technology
More case studies
HIPAA-compliant conversational AI for a UK healthcare company
A multi-agent conversational platform for patients, built for a regulated environment where every answer has to be traceable.
Architecture and technical roadmap for four concurrent AI platforms
Set the technical direction for four AI products at once: a real-time voice toolkit, public-sector agent systems, and a compliance-aware financial agent for Australia.
Product strategy and pivot for a no-code conversational AI startup
Took a no-code conversational AI platform from idea to MVP, validated it with customers, and pivoted to where the demand was.
Planning something similar?
Tell me what you're trying to achieve. I reply within 24 hours with a suggested next step.