Use case type
Provides natural-language interfaces that answer questions, guide users, and complete common tasks. It helps employees or customers access information and support without relying on manual service channels.
23
23
9
17 mo
Adoption over time
By case publish month · completed months only
23 cases documented across 37 months (Jul 23 – Jul 26), peaking at 3 in September 2025.
Each column counts every documented case of this type by its publish month, across the full corpus. The in-progress current month is excluded from columns and surfaced separately, and cases published before the charted window are summarized as earlier cases instead of plotted.
Company examples
10 shown from 23 use cases
Shopify co-developed the Universal Commerce Protocol with Google and built the Sidekick assistant on Google Cloud to support millions of merchants with agentic commerce experiences, conversational assistance, data-driven decision support, and action execution.
Velatura built Consent Manager+ to help patients understand complex healthcare consent forms with culturally and linguistically accurate explanations in near real time.The solution uses Falcon models on Amazon SageMaker AI with AWS services including Amazon S3, AWS Lambda, Amazon API Gateway, and related model access via Amazon SageMaker JumpStart and Amazon Bedrock Marketplace.
The All England Lawn Tennis Club modernized Wimbledon’s digital platforms to deliver personalized and interactive fan experiences using live match content and archive assets.The solution uses IBM watsonx Orchestrate for Match Chat and IBM Bob to build a knowledge graph, map content relationships, and translate the archive into a redesigned digital platform.The modernized experience includes Likelihood to Win, Key Moments explanations, and conversational Match Chat for the Wimbledon app and website.
OtherMyndYou developed 'Eleanor,' an AI-powered virtual care assistant, to improve patient engagement and chronic disease management amid US healthcare staffing shortages.Eleanor conducts complex clinical phone conversations, understanding both content and speech patterns to identify clinically relevant events and rank urgency.The solution uses Google Cloud Gemini large language models fine-tuned on clinical conversation data to accurately interpret patient responses.BigQuery analytics optimize call timing and maximize patient reach and engagement.HIPAA-compliant PaLM 2 large language model within Vertex AI is used for continuous service improvement without compromising patient data privacy.
TP ICAP's Innovation Lab built ClientIQ, a production-ready CRM assistant for searching and summarizing tens of thousands of Salesforce vendor meeting notes.The solution uses Amazon Bedrock Knowledge Bases for RAG, Amazon Bedrock Evaluations for automated quality testing, and a text-to-SQL path for structured queries.It includes permission-aware retrieval with Okta group claims, source attribution, custom ingestion from Salesforce to Amazon S3, OpenSearch Serverless vector search, and CI/CD evaluation.The article reports that after launch with 20 users, research time fell by about 75% and insight quality improved.
Innovaccer, a healthcare AI company, built a healthcare intelligence platform using Amazon Bedrock AgentCore to address data silos, complex workflows, and regulatory compliance in healthcare.The platform enables secure, scalable AI agents that integrate with healthcare data and tools via MCP-compatible APIs, supporting tasks like immunization scheduling and appointment booking conversationally.Innovaccer's platform manages over 80 million unified health records and has generated $1.5 billion in cost savings, demonstrating significant ROI from AI agent deployment in healthcare.
Seattle Children’s Hospital and Google Cloud built Pathway Assistant, a multimodal AI chatbot for clinical pathways.The assistant uses Gemini to extract metadata from PDFs, stores the secure document library in Google Cloud Storage, and grounds answers in pathway documents including diagrams and flowcharts.
Skello, a France-based HR workforce management SaaS platform, built an AI-powered assistant for end users to query workforce data in natural language while preserving multi-tenant data isolation and GDPR compliance.The assistant uses Amazon Bedrock, Amazon Bedrock Guardrails, and AWS Lambda to translate questions into structured database queries, enforce role-based access controls, and generate visualizations automatically.
The Government of the City of Buenos Aires introduced Boti, a WhatsApp-based AI assistant, to help citizens access city information and government procedures.To better answer questions about more than 1,300 procedures, the city and AWS built an agentic AI system with Amazon Bedrock, Bedrock Knowledge Bases, and LangGraph.
Amazon’s Worldwide Returns & ReCommerce (WWRR) organization built the Returns & ReCommerce Data Assist (RRDA), a generative AI conversational interface for self-serve analytics and validated SQL generation.RRDA empowers over 4,000 non-technical users to identify metrics, construct validated SQL, and generate visualizations through natural conversation.
Common questions
