Mobileye, an autonomous driving company with more than 230 million EyeQ system-on-chips deployed across roughly 1,200 vehicle models, used Amazon Bedrock AgentCore to deploy an AI Support Agent that cut response times by 90% and exceeded 95% accuracy targets, with zero infrastructure overhead. The company’s Data Collection Processing pipeline ingests thousands of drive-recording sessions daily, generating status inquiries from engineers and data teams. Previously, each inquiry required manual steps across multiple systems, and 66% of support tickets became routine status inquiries requiring engineers to manually navigate 15 clicks across multiple backend systems. Traditional automation approaches proved inadequate due to a lack of contextual understanding. Before full production rollout, Mobileye conducted a proof of concept targeting 95% accuracy in ticket classification with sub-2-minute response times. The agent uses Anthropic Claude foundation models, accessed through Mobileye’s internal LLM Gateway, which provides governed, quota-managed access to foundation models on Amazon Bedrock. The Model Context Protocol (MCP) enabled real-time access to the drive-data processing platform’s APIs, allowing the agent to query session status, retrieve processing logs, and pull diagnostic information during inference. The results led Mobileye to transform AgentCore into a self-service platform for teams across the company to deploy their own AI agents, using a hybrid architecture that bridges on-premises systems with AWS cloud services.