Automating customer service resolutions

NVIDIA partnered with Google Cloud to enable on-premises agentic AI by integrating Google Gemini models with NVIDIA Blackwell platforms and Confidential Computing, ensuring data sovereignty and regulatory compliance for sensitive enterprise operations. The solution further optimizes AI inference and observability by deploying a GKE Inference Gateway alongside NVIDIA Triton Inference Server, NVIDIA NeMo Guardrails, and NVIDIA Dynamo to enhance secure routing and load balancing for enterprise workloads.

Intuit integrated Google Cloud’s Document AI and Gemini models into its GenOS platform to automate the autofill of ten common U.S. tax forms, including complex 1099 and 1040 forms. The solution extracts and categorizes data from uploaded documents, drastically reducing manual data entry for TurboTax customers. This integration streamlines tax preparation workflows and improves speed and accuracy.

Capgemini partnered with Google Cloud to develop industry-specific agentic AI solutions that automate customer request handling across multiple channels such as web, social, and phone. The implementation integrates Google Agentspace, Customer Engagement Suite, and Agent2Agent interoperability protocol into existing customer service infrastructures to enhance personalized support, call routing, and workflow automation. This advanced solution transforms customer experience by streamlining communications and enabling proactive engagement.

Notion reimagined its platform by deeply integrating OpenAI’s GPT‑4o, GPT‑4o mini, and embeddings across its core features. They prototyped an AI writing assistant during a hackathon and then built internal tools to rapidly evaluate and deploy new models, transforming workflows in search, note-taking, and knowledge management from static content to interactive, actionable insights.

Zendesk integrated OpenAI's models to create adaptive AI service agents that autonomously manage customer conversations and execute resolution tasks. They implemented a multi-agent architecture featuring task identification, conversational RAG, procedure compilation, and procedure execution agents integrated with existing support workflows through API calls and natural language procedure definitions, while providing real-time chain-of-thought visibility. This solution transitions from traditional intent-based bots to a hybrid model of scripted and generative reasoning, streamlining customer service processes.

Hebbia built Matrix, a multi-agent AI platform that orchestrates OpenAI models including o3‑mini, o1, and GPT‑4o to automate complex financial and legal research tasks. The platform decomposes intricate queries into structured analytical steps and integrates modules like OCR, hallucination validation, and artifact generation to process complete documents, creating an infinite effective context window. This solution streamlines due diligence, contract review, and market research workflows, drastically reducing manual processing time.

Cox Automotive integrated Claude via Amazon Bedrock into its portfolio by first creating a sandbox environment to evaluate performance metrics and then selecting Claude 3.5 Sonnet for complex tasks and Claude 3.5 Haiku for high-volume content generation. They automated personalized dealer-consumer communications, generated engaging vehicle listing descriptions, and produced SEO-optimized blog posts, while also streamlining internal data governance through automated metadata generation. This integration optimized operational efficiency across marketing and internal data processes.

Intuit integrated Google Cloud’s Document AI and Gemini models into its GenOS platform to automate the autofill of ten common U.S. tax forms, including complex 1099 and 1040 forms. The solution extracts and categorizes data from uploaded documents, drastically reducing manual data entry for TurboTax customers. This integration streamlines tax preparation workflows and improves speed and accuracy.

Block implemented Anthropic’s Claude models (Claude 3.5 Sonnet and Claude 3.7 Sonnet) on its Databricks platform to power its internal AI agent, codename goose. They integrated the LLM using secure OAuth-enabled connections and a custom MCP server to connect internal databases and tools, enabling employees across all roles to auto-generate SQL queries, analyze complex data, and automate workflows. This agentic integration streamlined software development, design prototyping, and data analysis by translating user intents into actionable insights.