Design LLM review summaries that resist prompt injection and PII leaks

Build a platform that takes customer product reviews from an online store and has a large language model summarize them for an internal dashboard.

The round centered on trust and safety: how you stop instructions hidden inside a review from steering the model, how you clean the input before it reaches the model, and how personal data in reviews stays out of prompts, summaries and logs. Cover the ingestion pipeline, the summarization step and how you would check the summaries before anyone sees them.