Unleashing Operational Efficiency at Car IQ with Google Cloud LLM-driven Intelligent AI Assistant

Solution

  • Quantiphi delivered a fully operational chatbot, leveraging Car IQ’s knowledge base – facilitating the retrieval of answers to user queries
  • A UI with feedback feature was seamlessly integrated into the chatbot, empowering Car IQ to provide input on the chatbot’s responses
  • These feedback entries were automatically stored in a database, contributing to ongoing enhancements in solution performance
  • The solution’s automation was achieved through Vertex AI pipelines, allowing the Car IQ team to efficiently update the knowledge base in under 10 minutes by creating a new pipeline run, ensuring swift and effective knowledge base updates

Results

Car IQ benefited from the creation of a reliable chatbot UI using Google Cloud LLM models, facilitating seamless access to answers from their internal knowledge base

US State Supreme Court accelerates case document analytics and reporting with Intelligent Document Processing

Solution

Quantiphi utilized QDox, its intelligent document processing solution powered by AWS, to digitize, classify, and extract key information from over 500,000 civil documents, including petitions, judgments, and cover sheets. Through a human-in-the-loop review process, Quantiphi ensured 100% extraction accuracy

Results

  • Automated document classification for Cover Sheets, Petitions and Judgements
  • Automated extraction of 8 essential data points from case files for courts, parishes, titles etc across printed as well as hand written texts
  • Digitized over 500,000 court documents

Transforming Citizen Experience with Generative AI-based Query Resolution

Solution

  • Implemented a generative AI-powered virtual agent for resolving queries across 40 internal departments, covering areas such as employment opportunities, foster care and adoption, housing, and the Department of Motor Vehicles
  • Enhanced visibility into agent performance through the creation of a virtual agent analytics dashboard on Looker, facilitating the extraction of actionable insights
  • Leveraged generative AI capabilities to enable the virtual agent to address queries using information from anywhere on the Sullivan website, which comprised over 6.3k URLs
  • Elevated constituent experience by enhancing the functionality of the existing chat widget to support session restarts and timeouts
  • Employed custom generators to refine virtual agent responses, ensuring accurate handling of outdated or incorrect information

Results

  • Reduced response times, enhanced citizen engagement, and provided accurate information, resulting in increased efficiency across the agency’s communication channels
  • The agency expressed satisfaction with the chatbot’s performance, acknowledging its positive impact on citizen engagement

“Quantiphi has been a key partner in our effort to Institute this new chatbot on the Sullivan County website. The team right down to a person was always very responsive & very prompt. We have debuted cutting-edge technology that has improved the lives of the people we serve and has certainly made the workflow of our staff more efficient.”

Dan Hust, Director of Communications, Sullivan County

Optimizing Nurse Scheduling with Predictive AI

Solution

  • Quantiphi enhanced the client’s nurse assignment workflow by replacing their slow, manual process with a modern, data-driven, AI-powered nurse scheduling tool. This tool aids charge nurses in distributing patients more fairly and efficiently.
  • The tool performs ingestion and harmonization of source data from four distict source systems including standardization of over 10 million HL7v2 messages.
  • The Web UI of the tool aggregates all necessary data, creates visualizations, and facilitates informed scheduling decisions, matching patient workload with nurse demand.

Results

  • Optimized resource allocation for peak efficiency is provided by our AI-powered nurse scheduling tool.
  • Improved agility in staffing is achieved through a data-driven and dynamic approach that enhances speed and accuracy over time according to demand.
  • Real-time data empowers frontline workers with informed decisions, skill-aligned resource placement, and consolidated inputs on common screens for streamlined operations.
  • Elevated patient care through fair workload distribution, staffing alignment, and enhanced nurse satisfaction.
  • Greater value realization is achieved through accurate information centralized in one source, easing labor challenges and enhancing operational efficiency.

“A new nurse on a hospital unit was overwhelmed due to a significantly higher patient load compared to her colleagues. The implementation of the AI-powered nurse scheduling tool identified this disparity during her shift, allowing for adjustments to be made. The nurse’s subsequent statement, “It made my voice heard, and my shift manageable,” underscores the value of the tool in addressing workload inequities and improving nurse well-being.”

Automating Medical Claims Processing for a Leading Broker

Solution

Dociphi, Quantiphi’s AI-powered intelligent document processing platform, transformed claims processing, by eliminating the need for the reviewer to manually process each and every claim document

  • Dociphi seamlessly ingested and classified invoices and medical records, used proprietary best-in-class machine learning models to extract information from a wide range of document formats and templates, even from handwritten documents
  • Dociphi’s proprietory models intelligently mapped the Macro Guarantees and ICD codes to each claim submission based on extracted data from the documents such as diagnosis, medical test, body part, etc
  • With Dociphi’s smart comparison screens to compare the extracted data from docs with system data and highlight all the discrepancies, reviewers can close claims faster.

Results

  • Creation of a comprehensive AI-driven claims processing workflow, that supports data extraction from complex tables & hierarchical data
  • ML Powered ICD and Macro Guarantee mapping
  • Improved claims handling efficiency for accelerated claims turnaround time
  • Reduction of manual efforts for claim adjusters thereby reducing operational cost

Transforming Customer Experience with GenAI Enabled Chatbot

Solution

Quantiphi successfully deployed a generative AI-enabled chatbot, powered by baioniq, which efficiently mitigates delays in responding to technical inquiries. The solution entails grasping client requirements, tailoring baioniq with relevant technical content, seamlessly integrating it into the support platform, and configuring an intuitive interface. It harnesses document analysis and real-time updates, incorporating an escalation mechanism for complex issues. Continuous enhancement is ensured through feedback and performance monitoring, with a strong focus on security and privacy compliance. This methodology enables the client to elevate customer support, reduce response times, and promptly deliver precise information to customers encountering technical challenges.

Results

  • Swift resolution of customer queries through the development of a GenAI chatbot.
  • Utilization of diverse document formats and chat history, enabling the chatbot to deliver accurate responses.
  • Introduction of supplementary functionalities enhances accessibility to information, further improving user experience.

Enhancing Learning Management in Life Sciences with baioniq

Solution

The solution entails replacing the Chat GPT 4-based assistant with Quantiphi’s baioniq on the client’s AWS infrastructure. It addresses inquiries from sales representatives regarding medication dosage and side effects by analyzing uploaded documents. Users span across various roles including Representatives, Managers, MSLs/Clinical Specialists, across departments such as Sales, Marketing, CL&D, and Med Affairs.

During the Proof of Concept phase, baioniq is deployed, integrated with S3 and ElasticSearch, and connected to the client’s environment via APIs. Management of licensing, performance monitoring, and User Acceptance Testing (UAT) will be overseen. Subsequent phases involve setting up APIs for baioniq in the client’s mobile app and Salesforce, onboarding customers, and conducting diverse UAT sessions with document uploads.

Results

  • Enhanced Real-time Responses
  • Increased Data Security and Privacy
  • Optimized Platform Performance

Driving Student Learning Outcomes via Content Recommendation Engine

Solution

 Quantiphi leveraged deep learning techniques to craft knowledge-tracing models aimed at shaping student learning achievements through a recommendation engine. The recommendation engine tracks students’ interactions with diverse learning resources over time, factoring in variables such as individual learning aptitudes and exercise complexities. Using these insights alongside students’ learning abilities, the recommendation engine proposes subsequent learning exercises and adjusts dynamically according to student proficiency levels.

The solution is built on AWS and leverages several AWS services. The recommendation engine is also integrated with their existing learning application and is designed to give the client complete control and visibility. 

Results

  • Improved personalized learning experiences for students
  • Increased engagement with learning materials

Enhancing Literacy Support Through an Advanced Browser Based Tutoring Platform

Solution

Quantiphi, in collaboration with AWS Professional Services, developed an innovative web application solution that transformed the tutoring experience for the client. Through seamless integration of video conferencing, interactive tools like freehand drawing and virtual flashcards, and robust ADA compliance features, the platform ensures an engaging and accessible learning environment for students.

Moreover, our solution streamlines session management by facilitating seamless scheduling and offering tutors enhanced visibility through Salesforce integration. Automated communication features ensure tutors and guardians stay informed, while comprehensive reporting functionalities enable effortless tracking of student progress and performance.

Results

  • Improved session efficiency through seamless tutoring experience.
  • Enhanced student progress tracking capabilities.
  • Increased tutor satisfaction with improved engagement and productivity.

AI Assistive Clinical Study Research Assistant

Solution

  • Quantiphi developed an AI-powered clinical study research assistant utilizing LLMs, revolutionizing the protocol authoring process. By seamlessly integrating with external sources like clinicaltrials.gov and PubMed, as well as internal documents such as historical protocols investigator brochures and design concept sheets, the solution streamlined the collection and summarization of pertinent information.
  • This approach addressed the client’s primary pain points of a time-consuming (more than 25 weeks) manual protocol authoring process by a team of 50+ members, variability in references, empowering users to generate concise, context-driven content for different protocol sections efficiently.
  • The solution’s competitive advantage lies in its ability to deliver comprehensive and tailored information swiftly, enhancing the overall efficiency and effectiveness of protocol authoring.

Results

  • The solution quickly assimilated information, streamlined content gathering, and facilitated efficient sharing through MS Word and CSV export compatibility.
  • Users reduced manual effort of protocol development by more than 10 weeks through contextual dialogue with the solution, obtaining desired responses promptly with specific inquiries.
  • Integration with internal docs and external authentication empowered client to seamlessly expand usage across various therapeutic areas.
  • Enhanced productivity, reduced turnaround time, and improved accuracy were observed, leading to a more streamlined and effective protocol authoring process which may potentially lead into saving more than $50M per trial