AI Document Classification

oklido uses artificial intelligence to automatically classify documents and extract key information.

How It Works

When you upload a document (or one arrives via email):

  1. Text Extraction - OCR and text parsing
  2. Classification - AI identifies the document type
  3. Entity Recognition - Key dates, amounts, and names are extracted
  4. Source Matching - AI suggests the document source
  5. Quality Check - Confidence scoring for accuracy

What Gets Extracted

Document Type

oklido recognises these categories:

TypeDescriptionExamples
Investment MemoFund overviews, investment summariesFund fact sheets, PPMs
Quarterly ReportPerformance updates, NAV statementsQ1/Q2/Q3/Q4 reports
Distribution NoticePayout notificationsDividend notices, distribution letters
Capital CallFunding requestsCapital call notices, drawdown requests
Tax DocumentTax-related documentsK-1s, tax certificates, 1099s
Legal DocumentLegal agreementsSubscription docs, amendments
CorrespondenceLetters and emailsCover letters, announcements

Key Information

The AI extracts:

  • Dates - Document date, reporting period, due dates
  • Amounts - Investment values, distributions, calls
  • Names - Fund names, manager names, counterparties
  • Reference Numbers - Account numbers, document IDs

Accuracy & Confidence

Confidence Scoring

Each classification includes a confidence score:

  • High (above 90%) - Very confident, auto-applied
  • Medium (70-90%) - Likely correct, review recommended
  • Low (below 70%) - Uncertain, manual review required

Improving Accuracy

The AI learns from your corrections:

  1. Review suggested classifications
  2. Correct any errors
  3. AI improves for similar documents

Manual Override

You can always override AI suggestions:

  1. Open the document
  2. Click "Edit" in the details panel
  3. Change the document type or source
  4. Save your changes

Your corrections help improve future classifications.

Supported Languages

Document classification works best with:

  • English - Full support
  • Other languages - Basic support (text extraction works, classification may be less accurate)

Processing Time

Document TypeTypical Time
Text-based PDF2-5 seconds
Scanned PDF (OCR)5-15 seconds
Large documentsUp to 30 seconds
Bulk uploadsQueued processing

Privacy & Security

Your documents are processed securely:

  • Encrypted in transit using TLS 1.3
  • Encrypted at rest using AES-256
  • EU data residency - All processing in London (AWS eu-west-2)
  • No third-party AI - Processing uses our own models
  • GDPR compliant - Full data subject rights

Learn more about security →

Limitations

The AI works best with:

  • Standard financial document formats
  • Clear, readable text
  • Documents in English

May struggle with:

  • Handwritten documents
  • Poor quality scans
  • Unusual document formats
  • Non-English languages