When should an assistant be evaluated?
Evaluation should begin before customization and continue through development and deployment. Early baselines help determine whether later training or application changes actually improve behavior.
Explore This Question
Search for additional explanations using these tools:
More FAQs in What are the main stages involved in building an AI assistant?
No. Most application teams can start with an existing model and focus on prompts, retrieval, tools, and evaluation. Pre-training is a separate, resource-intensive undertaking.
No. An existing assistant model may already perform the task well with clear instructions and relevant context. Fine-tuning should address a demonstrated behavior gap.
Still have questions?
Browse all our FAQs or reach out to our support team