Which Bedrock feature compares models on your own tasks?
Why A is the answer
Amazon Bedrock Model Evaluations
Amazon Bedrock Model Evaluations compares models systematically on your own tasks.
In detail
- Model Evaluations compares models on your own tasks.
- Use your own dataset.
Use case
An illustrative scenario, not a real incident.
A team uses Bedrock Model Evaluations to compare two models on its own support tasks.
See it in different ways
flowchart TD A["GenAI evaluation"] --> B["Retrieval: did it find the right passages?"] A --> C["Model: accuracy and relevance"] A --> D["Agent: task completion"] A --> E["Users: feedback"]
stateDiagram-v2 [*] --> InspectLogs InspectLogs --> Retrieval: wrong context InspectLogs --> Prompt: right context, wrong answer Retrieval --> Evaluate Prompt --> Evaluate Evaluate --> [*]
flowchart LR S0["Prepare tasks"] --> S1["Run evaluation"] --> S2["Compare results"]
Key point: Model Evaluations compares models.
Why the other options are wrong
- B. AWS Budgets alerts
- Budgets tracks spending.
- C. Amazon Route 53 health checks
- Health checks test endpoints.
- D. AWS Config rules
- Config tracks resources.