Use logs to analyze, optimize, and fine-tune AI.
Analyze model usage
Query logs to understand usage, trouble shoot problems, calculate COGS, and evaluate models.
Optimize AI features
Enable caching and batching to reduce costs and latency. Test different prompts and models.
Run experiments
Select datasets to run one-off or continuous experiments. Test models, settings, and metrics.
Implement fine-tuning & batch
Generate training sets for fine-tuning. Use the batch API for evaluations, classification, or embeddings.
Email us at team@usevelvet.com.
