Module 4 of 5Lesson 2 of 3~14 min
Plan the fallbacks
When the model does not answer, or answers badly, users should never be left staring at an empty screen. This lesson teaches you to specify a chain of backup options, from a retry to a handoff to a human, and to choose for each kind of failure the one that still helps the user.
Lesson objective
By the end of this lesson, you will be able to specify the fallback chain of an AI feature (bounded retries, maximum wait, backup model, degraded mode, handoff to a human) and choose, for each type of failure, the fallback that stays useful for the user.
Topics covered
- fallback
- degraded mode
- resilience
- backup model
Where it fits
Incidents, fallbacks and model changes
What do you do when quality, the provider or the model shifts under your feet?
Lessons in this module
- Recognize AI-specific incidents
- Plan the fallbacks (this lesson)
- Change models without regressions
What you will learn in this module
This lesson is part of the course Ship and monitor an AI feature in production
- Diagnose AI-specific incidents (drift, provider outage, deprecation, call loop, cost spike) and plan the right fallbacks.
- Run a model or prompt change with regression evaluations, shadow comparison, staged rollout and a rollback plan.
Related courses
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Build an AI assistant for your product
3 hr
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Design a RAG architecture that fits your product
3 hr 30 min
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Evaluate an AI feature: test sets, metrics and LLM judges
3 hr