We scan new podcasts and send you the top 5 insights daily.
Florent describes the ideal complaint check: match the issue to a hazard in the risk file, find the acceptable failure rate, count similar events over 12 months, then divide by sales or install base. Nobody does this because gathering and correlating the data is too much work; Smartiva's AI does it in real time.
AI audits are not a one-time, "risk-free" certification but an iterative process with quarterly re-audits. They quantify risk by finding vulnerabilities (which can initially have failure rates as high as 25%) and then measuring the improvement—often a 90% drop—after safeguards are implemented, giving enterprises a data-driven basis for trust.
SaaStr's AI customer success agent flagged sponsors at risk of non-renewal by identifying those who complained frequently or never engaged with the portal. These are objective digital signals that a human CSM might ignore, downplay, or miss entirely amidst other responsibilities.
Florent gives a risk file as the example: pre-market teams build it for approval, and post-market teams could compare real-world complaints against it, including acceptable failure rates. But in most companies the pre-market and post-market groups and their data do not talk to each other.
To manage immense feedback volume, Microsoft applies AI to identify high-quality, specific, and actionable comments from over 4 million annual submissions. This allows their team to bypass low-quality noise and focus resources on implementing changes that directly improve the customer experience.
When customers blame your product for external failures you can't control (e.g., an SMS isn't delivered), don't dismiss the feedback. This often signals a need for better error handling or resilience. Use it as a prompt to build fallback mechanisms or better user notifications, thereby improving the overall experience.
Florent says complaints, adverse events, field service and repairs are continuous signals from the field. Most medical device companies only collect that data; the missing piece is recognizing signals from noise and taking action. That gap makes recalls look like visibility failures, not just isolated engineering failures.
The traditional Quarterly Business Review (QBR) is an outdated, reactive process based on past events. An AI agent can act as a continuous, real-time QBR, constantly monitoring customer progress, identifying gaps, and proactively engaging them, preventing issues before they happen.
Florent says an MDR contains registration, product and event information that already exists; only the manufacturer response and event description need careful judgment. Smartiva demonstrated a three-minute AI-assisted MDR submission so customers can spend time on patient safety and product improvement instead of filling out forms.
Florent says post-market surveillance falls between customer service, quality and regulatory but is not exactly any of them. Complaints contain heavy customer-service work and needs that a typical quality management system does not cover, at larger volumes and complexity. That gap kept the space underinvested and led him to start Smartiva.
Leaders championing AI for efficiency often overlook the devastating brand and business impact of the small percentage of interactions where AI fails. The key is not to expect perfection, but to have a robust strategy for managing these inevitable failures.