Blog

Once we heard about Amplitude’s successful AI Week, we knew we had to host our own for our Product & Engineering group. We even managed to get Wade from Amplitude to come talk to us.

Our AI Week sessions included

• LLM Internals — what’s inside the black box, and why does that matter?
• Prompt Best Practices — good prompts aren’t easy.
• Our internal AI architecture — so we can ensure the uniformity and centralized management needed for compliance, security, and to keep our costs under control.
• UI Toolkit for AI — our UX team created one design language and toolkit to bring our AI-based solutions to life, whether a team is building for Assistant, Insight, or Agent experiences.
• Developer Reference Store — a prototype repository to ensure the highest consistency from prompt-based features.
• Effective context management — Aman Singla, from Immersa, on getting the LLM to reason effectively through tasks, not just retrieve answers.
• Shipping AI products — Wade Chambers, from Amplitude, shared their experiences.
• A review of in-flight AI projects — we set a goal of 50 such projects by fiscal year end.

And we saw Windsurf, Claude, Cursor, Gemini, Vercel, and Trupeer used in our hands-on practical sessions.

We’re not new to the AI game

Zuora started leveraging machine learning long before ChatGPT’s big debut. Back in 2021, we leveraged our database of tens of millions of anonymized payments across different card networks, countries, and payment gateways to predict when the next payment retry should be attempted. This became our Smart Retry feature — customers measure its success using the additional dollars our 20% higher retry collection rates provide.

We’ve already shipped other AI-based features, from an AI assistant for querying metrics that doesn’t necessitate sharing your tenant’s data with the LLM, to our Order Entry feature that accepts a PDF of a contract or signed quote and builds a Zuora Billing Order for you to review before invoicing.

Reminder: Our public AI policy document guides all this work. We’ll always be clear when we are using AI, and we’ll safeguard your data just as we always have. AI should augment and empower humans, not replace them.