Production AI Systems: sections and modules
T4.6
Scaling and reliability
Scale ingestion and serving; plan failure handling.
About 2 h 56 min: 41 min reading + 2 h 15 min practice · 6 lessons
- Scope
- Scale and reliability
Lessons
Start module- 3Capacity, Latency, and Cost at Scale
7 min · Credited source
Also used in this module
Lessons taught in another module that this one builds on.
- Scale a Prototype from 100 to 100,000 Users
34 min · Opens the practice page
- Consumer-Scale Chat Service
44 min · Opens the practice page
- High-Volume Batch Inference Pipeline
1 h 1 min · Opens the practice page
Practise and Check
- Deliverable
- Scaling plan for 20M documents and a degradation ladder
- Assessment
- Checkpoint
- Interview probe
- What breaks at 100×?
- Common mistakes
- No backpressure or degradation plan
Your Progress
Saved in this browser when you leave the box.