Learn how Pydantic AI's agent framework enabled a hallucination-free, multilingual chatbot that seamlessly handles both English and Arabic for journalist training.
Media
From 1% response rate to AI-powered journalism training
ARIJ Network, connecting investigative journalists across 22 countries in the Middle East and North Africa, partnered with Vstorm to build a RAG-based AI chatbot using Pydantic AI. The bilingual system (English/Arabic) transformed their training process from handling just 1% of inquiries to delivering reliable, fact-checked knowledge at scale while creating new revenue streams.
“Using the PydanticAI framework, it was possible to build the agent itself and a set of tools: one to connect with the database, and one to validate the answers and ensure their language correctness. With that, the agent itself could deliver the best response possible.”— Vstorm, ARIJ Network
Products Used:
Pydantic AI
5 mins
Related case studies
View all case studies
Datalayer, a startup building AI-powered data analysis tools for Jupyter users, adopted Pydantic AI and Logfire after evaluating the agent frameworks market. With Pydantic AI's readable API and type safety, and Logfire's OpenTelemetry-based observability, they built a multi-protocol agent platform supporting AG-UI, ACP, Vercel AI, and A2A.
Read more→
Lema AI evaluated several agent frameworks before choosing Pydantic AI for its structured output validation, intuitive API, and seamless integration with Pydantic Logfire (our AI Observability Platform). The switch was a turning point in building their Agentic Risk Engineer - an autonomous system that investigates third-party security with forensic depth.
Read more→
Explore Logfire
Explore our open source packages
