Claro Platform
Confidence Scoring & Citations
Every AI output in Claro includes reliability metrics and full source traceability, so you know exactly which results to trust.
Understanding Confidence Scores
Claro calculates confidence using four key factors:
1. Source Reliability (40% weight) - How trustworthy are the information sources?
- First-party documents and authoritative sites score higher
- Unknown or low-trust sources reduce confidence
- Knowledge Base content typically scores higher than web sources
2. Content Consistency (30% weight) - How well do multiple sources agree?
- Consistent information across sources increases confidence
- Conflicting data from different sources lowers the score
- Single-source answers receive moderate confidence
3. Model Certainty (20% weight) - How confident was the AI model in its response?
- Low response variance indicates higher model certainty
- High variance suggests the model was uncertain
- Based on internal probability distributions
4. Retrieval Quality (10% weight) - How relevant were the source materials?
- Strong semantic match between query and sources
- Comprehensive coverage of the question topic
- Clear, well-structured source content
Confidence Badges
| Badge | Score Range | Color | What It Means |
|---|---|---|---|
| High | 85–100 | 🟢 Green | Highly reliable, ready to use |
| Medium | 60–84 | 🟡 Yellow | Generally good, worth spot-checking |
| Low | 0–59 | 🔴 Red | Needs human review or re-processing |
Working with Citations
Viewing Citations:
- Hover over confidence badges for a preview
- Click badges to see full source list and relevant passages
- Follow links to verify information in original sources
Citation Types:
- Knowledge Base: Page numbers and document names
- Web sources: URLs and relevant text snippets
- Geolocation: Map services and data providers
- File extraction: Document sections and page references
Optimizing Confidence Scores
To increase confidence:
- Add relevant Knowledge Bases with authoritative information
- Use specific prompts that clearly define what you need
- Provide examples of the desired output format in the prompts
- Cross-reference multiple sources when possible
When confidence is low:
- Refine your prompt to be more specific
- Add relevant reference documents to the Knowledge Bases
- Re-run individual rows with adjusted parameters
- Consider manual review for critical data points
💡 Pro Tips:
- Sort tables by confidence after large runs to prioritize review
- Set confidence thresholds in Column Settings to auto-filter results
- Use feedback loops (Dedicated plan) to train models on edge cases