{"slug":"giles-ai-delivers-95-accuracy-in-data-extraction-with-vertex-ai-and-gemini","url":"https://findausecase.com/use-cases/giles-ai-delivers-95-accuracy-in-data-extraction-with-vertex-ai-and-gemini","title":"Giles AI delivers 95% accuracy in data extraction with Vertex AI and Gemini","description":"London-based Giles AI built its giles research assistant on Google Cloud's Vertex AI and Gemini, using Document AI to parse medical literature, achieving 95% accuracy in data extraction, an 85% reduction in time required for clinical research tasks, and a 98% agreement rate between the AI and human researchers.","company":"Giles AI","industry":"Healthcare","country":"United Kingdom","aiCapabilities":["Document Intelligence","Generative AI"],"technology":["Vertex AI","Gemini","Gemini Pro","Document AI","Model Garden on Vertex AI","Gemma","Google Kubernetes Engine (GKE)","Cloud Run"],"deployment":"Unknown","problemStatement":"Bringing a new drug to market takes 10-12 years, a third spent on research, with scientists forced to trawl through over 40 million PubMed articles to find insights; healthcare professionals also distrust large language models that hallucinate answers, and Giles AI's prior multi-cloud, third-party-model architecture made healthcare compliance like HIPAA and SOC2 harder to achieve.","solutionApproach":"Giles AI migrated to Google Cloud with partner Insight managing the infrastructure landing platform, and built its giles® research assistant on Vertex AI and Gemini, using Document AI to parse unstructured medical literature and Gemini Pro's reasoning to extract and summarize data, admitting when data isn't available rather than hallucinating, with Model Garden letting the team swap in models like Gemma for clients needing data residency, and GKE/Cloud Run reducing latency for features like text-to-speech.","businessValue":"Giles AI achieves 95% accuracy in medical research data extraction, a 98% agreement rate between its AI and human researchers, and one customer saw an 85% reduction in time required for clinical research tasks; the company is also exploring multimodal features (Gemini Live, MedGemma, TxGemma) to expand into image analysis and real-time meeting insights.","evidence":{"band":"high"},"sourceUrl":"https://cloud.google.com/customers/giles","dates":{"publishedAt":"2026-10-01T05:49:31.145Z","publishedAtSource":"pipeline","updatedAt":"2026-10-01T05:49:31.145Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/giles-ai-delivers-95-accuracy-in-data-extraction-with-vertex-ai-and-gemini. Bulk republication requires permission."}