AI Security, Resilience & Multimodal
Real deployments don't get a well-behaved model or a healthy provider for free — prompt injection defense, timeouts and circuit breakers, and the vision, image, and audio APIs beyond plain chat.
AI Security: Prompt Injection & Output Validation
Three real attacks against the support agent in one sprint — a system-prompt extraction attempt, a poisoned policy document, and a poisoned tool result — and the defenses that actually hold up against each.
Resilience Patterns: Timeouts, Retries & Circuit Breakers
A provider outage during peak volume takes down more than the support bot — it exhausts the thread pool and drags down the whole app. Timeouts, Resilience4j, and a fallback that actually keeps the app up.
Multimodal: Vision & Document Understanding
Mobile check deposit and transaction-dispute screenshots — giving the support agent eyes with Spring AI's Media API, combined with the structured output and injection-defense lessons already built into this roadmap.
Multimodal: Image Generation & Audio
A voice support line that reuses the entire existing chat pipeline unchanged — transcription in, the same SupportChatService in the middle, speech synthesis out — plus image generation for auto-illustrated reports.