Avoiding AI Vendor Lock-In with a Multi-Model Strategy Quiz

Answers and explanations appear as you take the quiz.

1. Why does switching to a new embedding model usually mean re-embedding the whole corpus?
   • New models refuse to read old databases
   • Vector databases delete vectors after a model change
   • Vectors from different embedding models are in different spaces and cannot be compared
   • Embeddings expire after a fixed number of days
2. What is the main purpose of an evaluation suite in a multi-model strategy?
   • To measure whether a candidate model meets quality standards on your real tasks before switching
   • To get a lower price from the current vendor
   • To encrypt prompts before they are sent
   • To train a new model from scratch
3. Why does putting every model behind one unified API not guarantee portability?
   • Unified APIs only work with open-source models
   • Unified APIs are always slower than direct calls
   • Unified APIs do not support streaming
   • Prompts tuned to one model's behavior often perform differently on another
4. Sending simple tagging tasks to a small model and complex complaints to a frontier model is an example of what?
   • Fine-tuning
   • Routing tasks by difficulty to control cost
   • Zero data retention
   • Re-embedding
5. What should be stored with every vector to make future re-indexing straightforward?
   • The user's password
   • The billing account number
   • The embedding model's name and version, along with source text and chunking settings
   • Only the vector dimensions
6. Which of these is an example of platform-feature lock-in?
   • Relying on a provider's hosted conversation threads and built-in vector store
   • Sending requests in JSON
   • Using HTTPS for API calls
   • Logging response latency
7. What is usually true of fine-tuned models on hosted provider platforms?
   • They can be downloaded and run anywhere
   • They automatically work with every other provider
   • They cost nothing to keep
   • They usually cannot be exported to another provider
8. What does canary routing mean when adopting a new model?
   • Switching all traffic at once overnight
   • Sending a small share of traffic to the new model and comparing results before widening
   • Testing only with synthetic data
   • Letting users choose their model manually