AI engineering$349/ seat
Production LLM apps
Build, evaluate and ship a retrieval-augmented assistant that holds up in production.
Workshop · June 9
Edge-first architecture
Design globally distributed apps that are fast everywhere and fail gracefully.
Overview
Kenji Watanabe walks you through the patterns Cloudline uses to serve 40 billion requests a day: where to put state, how to cache without lying to users and what to do when a region disappears.
Hands-on labs use a simulated global network so you can break things safely.
Highlights
Data placement
Choose between replication, sharding and regional pinning.
Caching strategies
Stale-while-revalidate and cache keys that scale.
Chaos labs
Take down a region and keep serving.
Latency budgets
Measure and defend p99 latency.
What's included
- Laptop with Docker installed
- Lab environment provided
- Architecture templates
- Lunch and coffee
- Certificate of completion
- Recording access for 90 days
Agenda
What really runs at the edge, and what shouldn't.
Replication patterns with hands-on exercises.
Build a cache layer and measure the difference.
Region failover drills and a group post-mortem.
More workshops
You might also like
AI engineering$349/ seat
Design$299/ seat
Design systems at scale
Tokens, components and governance for systems used by hundreds of teams.
Security$299/ seat
Threat modelling for product teams
A practical, no-jargon method to find security issues before attackers do.