Agentic AI at the Edge: Building Mobile AI Agents for Automotive & MedTech

Shipping AI into regulated, safety-critical mobile apps is more than “just call an LLM.” In automotive and medical contexts, we must meet strict privacy, latency, and auditability requirements while working with flaky connectivity and device constraints. In this talk, Ronak will share a field-tested architecture for agentic AI on the edge: a hybrid edge–cloud agent that uses tool-calling plugins, a policy engine for pre/post-prompt guardrails, offline fallbacks, and structured telemetry for audits. He will walk through how his team bounds agent behavior with capability cards, redacts PHI/PII at the prompt boundary, use function-calling for deterministic actions, and runs evaluation harnesses that catch regressions before release. He will cover mobile-specific realities—BLE/IoT device flows, background execution limits, and battery/perf budgets—and how to pass security and compliance reviews without derailing delivery. Attendees leave with a blueprint (components, sequence flow, and code-level patterns) plus a checklist for governance, observability, and safe rollout. If you build AI into mobile apps for cars or clinics, this session gives you the patterns, the pitfalls, and the guardrails to move from prototype to production.