Brief in progress — review the script and demo before recording.
This lesson is about everything that happens after a product or feature is released. Most developers are not especially interested in this stage, beyond error logs or telemetry. We will need to show some tools for observability, monitoring (Sentry / PostHog?), customer support, and similar. Students probably already know most of them, but they may have no idea how this data can be used with AI today.
- Signals: people need to understand “where to look” and “what to look for” from a Product Engineering point of view. We need to show them that AI itself changes the game here, and explain what exactly changes — especially when AI connects the dots between signals across many sources.
- Observability: observability of the app has become critical, and it has changed in many ways if the product uses AI — and most of them do. That includes monitoring activity, cost, and latency, as well as the quality of the interaction. (Note: Angie’s week covers observability and evals, but we still need to mention them from our perspective.)
- Decisions: all of this data can be analyzed, mostly anonymously, but it brings no value without a follow-up. A critical part of this lesson is building a process in which AI gives us insights that affect product decisions — at the development level, in product management, or across the business.
We may want to showcase scenarios such as:
- Workflows you already have in Kody. One example: turning user interactions into an event stream that AI can look into and shape into an ongoing onboarding — a scenario where the user is guided not only through the features of a product, but through those features in their own context.