Robert Ta describes Booking.com's AI observability system, which collects traces from GenAI apps, redacts PII through a dedicated service, streams data to Kafka, and sends it to both a real-time platform and a data warehouse. The architecture splits into modular, independently scalable components to handle enterprise-scale workloads.
This is how Booking.com scales AI observability with Arise. To those that are interested in enterprise architectures and responsible for figuring out what is a scalable architecture to meet our AI adoption and AI-native development needs going forward as a technology team, I found this to be a very interesting use case. This is a really interesting diagram to kind of ground on in terms of their architecture. So on the left, you have N number of GenAI applications. They're using an AI telemetry collector. They pull that in, they normalize it, and then they have traces going into a secure message bus. In this case, it looks like they are using a managed Kafka service. So that's a durable buffer that absorbs spikes and decouples producers from consumers. And then they have a PII redaction service. I thought this was really interesting for anybody in enterprise software that has to deal with compliance and regulation and privacy and things like that. So they specifically call that out in their architecture that they have a service that detects and masks PII in span attributes and text fields. And then they go and export to Arise and a warehouse. Redacted traces are sent to Arise in real time and stored in the warehouse for analytics. Arise will then enrich with space project metadata, etc. And then on the warehouse ingestion side, it looks like these persist to use for offline analytics, long-term trends and backfills. And here's another diagram for their ML prediction log pipeline for Booking.com from their data warehouse all the way to Arise and then getting to specific datasets that they could use for GenAI applications such as ranking or fraud detection or any other model that they could then fine-tune for domain-specific problems. One of the biggest takeaways from reading this to me was everybody that is deploying AI architectures at scale, you really need to be thinking about chunking out their services so that you could do this at scale.
