This section applies to assessments using the Upload intake mode. Skip to Step 4 if using Guided Interview or Manual Entry.
1
Upload business document
Drag and drop or click to select a PDF/DOCX file (max 10MB):
Supported formats:- PDF (.pdf)- Microsoft Word (.docx)File size limit: 10 MB
2
Trigger document parsing
Click Parse Document to start AI extraction. This creates an asynchronous job.The system will:
Upload file to S3 with pre-signed URL
Create a PARSE_DOCUMENT job
Invoke Worker Lambda with Claude 3.5 Sonnet v2
Extract structured data across all 35 risk indicators
3
Monitor parsing progress
A progress indicator shows the current job status:
Pending: Job queued for processing
Processing: AI is extracting data (typically 30-60 seconds)
Completed: Data extracted successfully
Failed: Error occurred (check error message)
API Request Pattern
// Create parse jobPOST /api/assessments/:id/documents/:documentId/parse// Frontend polls every 3 secondsGET /api/jobs/:jobId// Stop polling when status is COMPLETED or FAILEDif (job.status === 'COMPLETED') { // Proceed to gap detection navigateTo('/assessments/gap-detector?id=' + assessmentId);}
4
Automatic gap detection
Upon successful parsing, the system automatically chains a GAP_DETECTION job to identify missing data fields.
Parsing and gap detection typically complete within 2 minutes. Large documents (>50 pages) may take up to 5 minutes.
Click each category card to expand subcategory details:
Individual subcategory scores (0-100)
Traffic light indicators (red/yellow/green)
Data sources and assumptions
4
Edit recommendations (optional)
Click Edit on any recommendation to:
Clarify language for the business owner
Add context-specific details
Adjust priority (High/Medium/Low)
PUT /api/assessments/:id/recommendations/:recId{ "editedText": "Diversify customer base by targeting 3-5 additional buyers in Q2 2026 to reduce revenue concentration below 25% per customer.", "priority": "HIGH"}
Original AI-generated text is preserved; your edits are stored separately.
Risk scores are recalculated automatically if you update data in the Gap Detector. Changes to gap fields do NOT trigger automatic re-analysis; you must manually click Re-analyze to refresh scores.
Risk Scorecard (all 7 categories with subcategory breakdowns)
Evidence and Narratives (category-level explanations)
Recommendations (prioritized by High/Medium/Low)
Appendices (data sources, methodology)
3
Generate PDF
Click Download PDF to trigger the REPORT_GENERATION job.The system will:
Fetch all assessment data (gaps, scores, recommendations, comments)
Render HTML template with data
Convert HTML to PDF using headless Chrome (AWS Lambda)
Upload PDF to S3
Return pre-signed download URL (expires in 1 hour)
4
Download and review
Once generation completes (typically 20-30 seconds):
Click the download link
Save the PDF locally
Review for accuracy and completeness
Share with stakeholders as needed
Generated PDFs are stored in S3 for 90 days. You can re-download from the Report page within this period. After 90 days, click Regenerate to create a new PDF.
// Search by company name, assessment name, or statusGET /api/assessments?search=acme&status=COMPLETE&limit=10Response: { data: Assessment[], total: number, nextCursor?: string // For pagination}