How Giles AI Achieves 95% Accuracy in Medical Literature Extraction with Gemini

Giles AI, a London-based healthcare AI startup, built its medical research assistant on Google Cloud using Vertex AI, Gemini Pro, and Document AI to help researchers extract structured insights from millions of scientific articles. The platform achieved 95% accuracy in data extraction, a 98% agreement rate with human researchers, and helped one clinical customer cut research task time by 85%.

Impact

95%

Medical research data extraction accuracy

85%

Clinical research task time reduction

98%

AI-to-human researcher agreement rate

Challenge

Medical literature review consumes years of drug development timelines, but healthcare AI must achieve near-perfect accuracy — any hallucination or fabricated citation can compromise clinical decisions. Giles AI’s prior fragmented architecture made compliance certifications difficult and model outputs insufficiently reliable for healthcare professionals.

Solution

Giles AI rebuilt on Google Cloud with Vertex AI and Gemini Pro for complex reasoning, Document AI for unstructured literature parsing, and Gemma for data-residency-constrained clients — delivering a HIPAA- and SOC2-compliant platform that explicitly admits when information is unavailable rather than hallucinating answers.

Tools & Technologies

What Leaders Say

The Google Cloud team was accessible from the outset, immediately introducing us to people who could help build the platform and grow the business. Without that support, along with compliance and medically focused AI models out of the box, it would have taken far longer to achieve our goals.

Rishi Wadhera, CEO and Co-founder, Giles AI

Thanks to Google Cloud, one customer achieved an 85% reduction in the time required for clinical research. The combination of Document AI and Gemini has also led to a 98% agreement rate between our AI and human researchers. Google Cloud allows us to deliver trusted, real-world insights faster than ever.

Rishi Wadhera, CEO and Co-founder, Giles AI
Get the full story.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

Full Story

Bringing a new drug to market typically takes 10 to 12 years, with roughly a third of that time consumed by literature review and evidence synthesis. Researchers must sift through databases like PubMed — which hosts over 40 million articles — to identify the specific evidence needed for a clinical trial or regulatory submission. The work is time-consuming, error-prone, and deeply consequential: a missed study or misread result can delay a therapy by years.

Giles AI was founded to compress this timeline. Its core product, giles®, is a research assistant designed to think like a healthcare professional — ingesting scientific literature and extracting structured, cited insights that researchers can trust. Trust is the critical constraint in healthcare AI: hallucinations that might be tolerable in other contexts are unacceptable when the output informs clinical decisions. Giles AI’s previous cloud provider could not supply the compliance infrastructure or the specialized AI capabilities the company needed, requiring it to stitch together multiple third-party solutions. The architectural fragmentation made HIPAA and SOC2 compliance significantly more difficult to achieve and maintain.

Migrating to Google Cloud with support from partner Insight, Giles AI rebuilt on a unified infrastructure. Vertex AI became the foundation for model orchestration, allowing the team to swap between Gemini models for complex reasoning and open-source models like Gemma for enterprise clients with data residency requirements. Document AI parses unstructured scientific literature — clinical studies, regulatory submissions, patents — and feeds structured outputs to Gemini Pro for analysis and synthesis. If the information needed isn’t present in the source material, the system explicitly says so rather than generating a plausible but false answer. This behavior was critical to gaining trust from clinical researchers.

The results are measurable. Giles AI now achieves 95% accuracy in medical data extraction. One clinical customer reduced the time required for research tasks by 85%. The AI’s outputs agree with those of human researchers at a rate of 98%. Google Kubernetes Engine and Cloud Run underpin the infrastructure layer, significantly reducing latency so that features like text-to-speech work instantaneously. The company achieved healthcare compliance out of the box, removing a significant barrier to enterprise adoption.

Giles AI is now expanding the platform from a research assistant toward a real-time collaborator capable of listening in on research meetings via Gemini Live, proactively surfacing relevant literature in context. Plans include integration with MedGemma and TxGemma for medical image analysis, and a launch on Google Cloud Marketplace to reach enterprise clients in Europe and Latin America without procurement friction. Giles AI CEO Rishi Wadhera estimates the 18 months of development the company has completed would have taken significantly longer without Google Cloud’s integrated infrastructure and direct team support.

Similar Cases

M
Morrisons
98.96%
data reporting lag reduction

Morrisons, one of the UK’s largest supermarkets serving nine million customers weekly across 500 stores, migrated its on-premise data warehouse to BigQuery and Looker, reducing reporting lag by 98.96% from one day to 15 minutes. Real-time data now powers Vertex AI demand forecasting models and a customer-facing Product Finder app that receives 50,000 hits per day during peak periods.

RetailVAVertex AIBBigQuery
FD
Fifth Dimension
Days or weeks → 30 minutes
investment memo drafting time

Fifth Dimension, a global AI platform for commercial real estate asset managers and owner-operators, built a multi-model workflow on Google Cloud using Gemini for large-scale document ingestion and Claude for high-precision reasoning. The platform compressed investment memo drafting from days or weeks to just 30 minutes and achieved 99.9% reliability for multi-hour workflows, driving deals with top-10 U.S. asset managers.

Real EstateVAVertex AIBBigQuery
CE
Class Editori
One of Italy’s first AI agents in the media landscape
mfgpt launch milestone

Class Editori, a leading Italian media company specializing in finance, fashion, and lifestyle with 40 years of content archives, partnered with Softlab to build MFGPT on Google Cloud — one of Italy’s first generative AI agents in the media industry. The system unified four decades of journalistic archives and real-time financial data into BigQuery, powered by Gemini and Vertex AI, converting trial users into paid subscribers and securing B2B enterprise agreements with major financial institutions.

Advertising & MediaVAVertex AIFFirestore
AS
AXA Switzerland
Over 95%
query and processing time reduction

AXA Switzerland, the country’s leading insurer covering over 40% of Swiss companies, migrated its entire data infrastructure to Google Cloud and deployed BigQuery, Vertex AI, and Gemini to become a data-driven organization. The transformation reduced complex query times from days to minutes or seconds and generated a high double-digit million Swiss franc profit improvement through Smart Data initiatives.

InsuranceVAVertex AIBBigQuery
FD
Fifth Dimension
50x
document processing capacity increase

Fifth Dimension, a UK-based AI analytics company serving the real estate industry, migrated to Google Cloud to overcome critical infrastructure bottlenecks. By adopting Vertex AI, Cloud Run, and serverless architecture, the company achieved 50x processing scalability, 6x revenue growth, and a 30% reduction in infrastructure costs — all within a rapid growth trajectory from founding in 2023 to global scale by 2025.

TechnologyVAVertex AIPPub/Sub
E
Etsy
~80x
listings per theme increase via algotorial curation

Etsy, the global marketplace for handcrafted and vintage goods, serves nearly 90 million buyers across more than 130 million listings from 5 million sellers. Using Vertex AI, BigQuery, Dataflow, and Gemini, the company built a personalized search and discovery platform it calls “algotorial curation” — increasing listings per theme by 80x, driving a 5% lift in SEO-driven visits, and delivering a 3% conversion improvement for sellers.

RetailVAVertex AIBBigQuery
A
AstraZeneca
40%
developer velocity increase with github copilot

AstraZeneca, one of the world’s largest pharmaceutical companies, unified 5,000 developers and scientists onto GitHub Enterprise, automated CI/CD with GitHub Actions, and deployed GitHub Copilot — achieving a 40% increase in developer velocity in its pilot program and generating 9 to 10 additional hours of productive output per developer each week. With drug development timelines measured in decades, the company views even marginal acceleration as directly impacting patient outcomes.

HealthcareGAGitHub ActionsGEGitHub Enterprise
ES
Epic Systems
Over 50%
claude code usage from non-developers

Epic Systems — the healthcare technology company behind MyChart, used by 195 million patients — deployed Claude Code across its entire workforce, not just engineers. Today, more than half of Claude Code usage at Epic comes from non-technical employees, including a pharmacist who built a fully interactive MyChart prototype without writing a single line of code.

HealthcareCClaudeCCClaude Code