Freelancer profile translated to English.
Back to original languageAbout Gabriel
Looking to automate your business processes, deploy reliable AI agents, or integrate your existing systems without breaking what works?
I build custom AI agents to automate your business processes. Voice agents, RAG pipelines, n8n workflows. Already deployed in schools in Canada and on pharma architectures (integration LIMS/CTMS/DMS via MCP).
For example:
→ Voice agents that talk to your clients in real-time
→ RAG pipelines on your internal documents (contracts, SOPs, knowledge bases)
→ n8n workflows: onboarding, follow-ups, email processing, reporting
→ Multi-system integrations via MCP (CRM, ERP, business databases)
→ Fine-tuning LLMs on your proprietary data
→ Custom internal AI tools (document search, report generation)
Among my recent achievements: ClassGenie (classgenie.ca), where AI voice agents help students practice languages in schools across Canada. Real-time conversations, pronunciation feedback, multi-model architecture with automatic fallback.
I also designed Snoopstr (snoopstr.com), a competitive intelligence agent that navigates complex websites, extracts structured data, and generates automated analyses (live demo on the website).
Over 10 years of product engineering experience behind this work. From large companies like Santander Bank to fast-growing startups, I adapt to your project's needs and scale.
I have developed my expertise not only in design but also in creating and marketing a product from A to Z, having designed SaaS products myself. In fact, I sold one of my projects, Chesskool, a chess education platform with over a thousand paying users.
French
Fluent
Spanish
Native or bilingual
English
Native or bilingual
Remote only
Primarily works remotely
Experience
- ClassGenie.caCo-founderMay 2025 - Today (1 year and 1 month)ClassGenie.ca, a platform created to optimize language learning in school systems.Some of the challenges we faced:Creating custom voice agents with minimal lag and maximum quality. Things that seem obvious when you see the end product are not when you develop it. For example, I used some live models like Gemini 2.5 live, which output text and audio at the same time.Well, funnily enough the text that Gemini 2.5 live outputted was not a 1:1 match with its audio, so I had to find a way around it by using a different transcription model (in this case, Elevenlabs scribe)Quality control agents. It's essential to have safeguards to control the quality of agents. But infinite quality control makes the agents slow and unusable. A key challenge was to find the right amount of safeguards that guarantees the system working well, while being as transparent as possible to the end user.Fallback models (I've learned this the hard way): Imagine your whole platform depending on a company like OpenAI not glitching. That's why almost all of our custom agents have fallback models.
- chesskool.comFounder (project sold)ENTERTAINMENT AND LEISUREMay 2022 - May 2025 (2 years and 11 months)Chesskool is a paid-membership web app I built using React and Meteor.js, where users learn chess through spaced repetition. Over 2,500 users.
- GotmyConsultorTECHMay 2020 - September 2021 (1 year and 4 months)Startup video streaming consultant:Application development.Product iteration across multiple phases to achieve a functional, incremental MVP.Product–market fit testing, from new idea conception to market feedback through experiments (Facebook ads, Instagram ads, etc.).
Reviews
Recommendations
These freelancer profiles also match your criteria
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Education
- Telecommunications EngineerUniversity of Seville2015