AI Performance & Quality
Response Quality
Improve how accurately and helpfully your chatbot answers customers.
Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available QwryAI pages before exploring further.
Response quality is the result of source coverage, retrieval quality, model behavior, and clear escalation rules. Review weak answers with the customer question, the source content, and the chatbot response side by side.
- Improve missing content first.
- Use Playground to retest the same wording after every change.
Quality Levers
| Lever | When to use it |
|---|---|
| Instructions | The chatbot knows the information but answers with the wrong tone or boundary. |
| Source updates | The answer is missing, outdated, vague, or hidden in unreadable content. |
| Model settings | The source is correct but reasoning, concision, or latency needs adjustment. |
| Escalation | The question needs account-specific, billing, or human judgement. |
- Clear source content
- Narrow prompt boundaries
- Correct model settings
- Escalation when information is missing
- Review of low-confidence or disliked answers