Skip to main content

Confidence scores

When importing design tokens, preset AI shows confidence scores to help you understand how reliable each extraction is. Higher confidence means more trustworthy results.

What confidence means

Confidence indicates how certain preset AI is about an extracted token's accuracy. It's displayed as a percentage or visual indicator:

LevelScoreVisualMeaning
Very high85%+Five filled dotsHighly reliable, parsed from standard format
High70-84%Four dotsLikely accurate, minor uncertainty
Medium50-69%Three dotsReview recommended
Low30-49%Two dotsManual verification needed
Very low<30%One dotMay be incorrect

Why confidence varies

Token extraction involves multiple stages, each adding potential uncertainty.

1. File detection

Did preset AI find the right files?

ScenarioConfidence
Standard file names (tokens.json, tailwind.config.js)High
Non-standard locations or namesLower
Files guessed from directory structureLow

2. Format parsing

Did preset AI understand the file format?

ScenarioConfidence
Tokens Studio with $metadataVery high
Standard Tailwind configHigh
CSS with clear :root custom propertiesHigh
Unknown JSON structureLower

3. Value extraction

Did preset AI extract the actual values correctly?

ScenarioConfidence
Direct value (e.g., #3b82f6)High
One level of reference resolvedSlightly lower
Multiple reference levels resolvedLower
AI-extracted from unstructured contentLow

4. Semantic mapping

Did preset AI map tokens to the right semantic meaning?

ScenarioConfidence
Exact name match (e.g., primary--primary)High
Pattern-based match (e.g., button-bg--primary)Medium
AI-inferred semantic meaningLower

How confidence is calculated

Confidence compounds across stages. If each stage is 90% confident:

0.90 × 0.90 × 0.90 × 0.90 = 0.66 (66%)

This is why even reliable-seeming extractions may show medium confidence: uncertainty accumulates.

Example breakdown

Token: design.color.brand.primary

StageConfidenceReason
Detection98%Found tokens.json with $metadata
Parsing95%Standard Tokens Studio format
Extraction90%Resolved two token references
Mapping85%Name contains "primary"
Compound71%0.98 × 0.95 × 0.90 × 0.85

Confidence by source

Different import sources produce different typical confidence levels:

Source formatTypical confidence
Tokens Studio85-95%
CSS Variables80-90%
Tailwind Config70-85%
Style Dictionary75-85%
AI Analysis25-50%

Tokens Studio files have the highest confidence because they use a well-defined schema with explicit metadata.

What to do with low confidence

For individual tokens

ConfidenceAction
High (70%+)Trust the extraction
Medium (50-69%)Quick visual check
Low (<50%)Verify value manually

For the overall import

If many tokens have low confidence:

  1. Check your source format: consider exporting to Tokens Studio or Style Dictionary
  2. Review flagged tokens: focus on low-confidence items first
  3. Verify critical tokens: especially primary colors, typography, spacing

Import summary

At the end of scanning, preset AI shows aggregate statistics:

Import Summary
--------------
Total tokens: 24
Average confidence: 78%
High confidence: 20 tokens (83%)
Low confidence: 2 tokens (8%)

Weakest stage: Mapping (avg 72%)

This helps you understand overall extraction quality before importing.

Improving confidence

Use standard formats

The most reliable extraction comes from:

  1. Tokens Studio: export from Figma plugin or create manually
  2. Style Dictionary: industry-standard token format
  3. CSS custom properties: in :root block with clear naming

Clear naming conventions

Tokens with semantic names are easier to map:

NamingConfidence impact
primary, background, destructiveHigher
blue-500, gray-100Medium
color1, c1, mainLower

Avoid deep references

Each level of token reference ({color.blue.500}{primitives.blue}#3b82f6) reduces confidence.

FAQ

Why does the same token have different confidence in light vs. dark mode?

Each mode is evaluated independently. If dark mode required more reference resolution, it may have lower confidence.

Can I import tokens even with low confidence?

Yes. Confidence is advisory: it helps you prioritize which tokens to verify, but doesn't block import.

Does confidence affect anything after import?

No. Once imported, all tokens are treated equally. Confidence is only shown during the import preview.

Why is AI extraction confidence so low?

AI analysis is probabilistic. While often accurate, there's inherent uncertainty in inferring structure from unstructured content. We're transparent about this uncertainty.

Can I see the confidence breakdown for each token?

During import preview, click on a token to see its detailed confidence breakdown by stage.

Was this page helpful?

Last reviewed by @jschuyler
All systems operationalDocsDevelopersPlatformPricing
PrivacyTerms© 2026 fndd, LLC