Prerequisites
Before starting, ensure you have:Account Access
A valid user account created by an administrator with your email address
Initial Password
The temporary password provided by your administrator (you’ll change this on first login)
Sample Data
A business plan document (PDF or DOCX) or business information ready for manual entry
Modern Browser
Chrome, Firefox, Safari, or Edge (latest version recommended)
Step 1: First Login and Password Setup
Complete password change
On first login, you’ll be prompted to set a new password. Your password must meet these requirements:
- Minimum 8 characters
- At least one uppercase letter
- At least one lowercase letter
- At least one number
- At least one special character (@$!%*?&)
Step 2: Create a New Assessment
Access the dashboard
After login, you’ll see the dashboard with assessment statistics:
- Total Assessments
- Completed
- Active (in progress)
- Drafts
Select intake mode
Choose one of three data collection methods:
- Upload
- Guided Interview
- Manual Entry
Best for: Businesses with existing business plans or pitch decksUpload PDF or DOCX files containing business information. The AI parser will extract:
- Company background and mission
- Financial projections and statements
- Market analysis and competitive landscape
- Operational details and supply chain
- Management team and governance
Step 3: Document Upload and Parsing
This section applies to assessments using the Upload intake mode. Skip to Step 4 if using Guided Interview or Manual Entry.
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_DOCUMENTjob - Invoke Worker Lambda with Claude 3.5 Sonnet v2
- Extract structured data across all 35 risk indicators
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
API Request Pattern
Step 4: Review and Fill Data Gaps
Navigate to Gap Detector
Click Review Gaps or navigate to the Gap Detector page from the assessment menu.
Review identified gaps
The system displays all 35 risk indicators grouped by category, each marked as:
- Verified (green): Data extracted and validated
- Partial (yellow): Data found but incomplete or low confidence
- Missing (red): No data found
Fill missing data
For each missing or partial field:
- Review the extracted value (if any)
- Enter the correct value or additional information
- Click Save to update the field
correctedValue field stores your input and takes precedence over extractedValue.Step 5: Run Risk Analysis
Trigger risk analysis
Click Analyze Risk to create a
RISK_ANALYSIS job.The AI agent will:- Score all 35 indicators on a 0-100 scale
- Map scores to risk levels: 0-33 (Low), 34-66 (Medium), 67-100 (High)
- Generate evidence-based narratives for each category
- Create prioritized recommendations
Review subcategory breakdowns
Click each category card to expand subcategory details:
- Individual subcategory scores (0-100)
- Traffic light indicators (red/yellow/green)
- Data sources and assumptions
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.
Step 6: Generate PDF Report
Navigate to Report page
From the Risk Scorecard, click Generate Report or navigate to the Report page.
Preview report sections
Review the report structure:
- Executive Summary (overall risk level + key findings)
- Company Profile (extracted from intake data)
- Risk Scorecard (all 7 categories with subcategory breakdowns)
- Evidence and Narratives (category-level explanations)
- Recommendations (prioritized by High/Medium/Low)
- Appendices (data sources, methodology)
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)
Step 7: Manage Assessments
Search and Filter
Use the dashboard search bar to find assessments:Assessment Statuses
DRAFT
Assessment created but not yet started. Intake mode selected, no data collected.
ANALYZING
Active jobs running (parsing, gap detection, or risk analysis in progress).
ACTION_REQUIRED
Gap detection complete, awaiting data input or corrections before analysis.
COMPLETE
Risk analysis finished, PDF report generated. Ready for review and export.
Edit or Delete Assessments
- Edit: Click the row in the dashboard table to navigate to the Gap Detector page
- Resume Draft: Click Resume on draft assessments to continue from the intake step
- Delete: Click the trash icon and confirm deletion (cannot be undone)
Next Steps
Architecture
Learn how the system works under the hood
API Reference
Explore all available API endpoints
User Management
Manage users and permissions (admin only)
Common Issues
Document parsing fails with 'Unsupported format' error
Document parsing fails with 'Unsupported format' error
Cause: The uploaded file is not a valid PDF or DOCX, or is corrupted.Solution:
- Verify file extension is
.pdfor.docx(not.doc,.odt, etc.) - Try opening the file locally to confirm it’s not corrupted
- Re-export from source application (Word, Google Docs) and re-upload
- If using scanned PDF, ensure it contains text (not just images)
Risk analysis job stuck in PROCESSING for >5 minutes
Risk analysis job stuck in PROCESSING for >5 minutes
Cause: Worker Lambda may have timed out or encountered a Bedrock throttling error.Solution:
- Refresh the page - job status may be stale
- Check if status changed to FAILED (error message will be displayed)
- If still PROCESSING, wait 2 more minutes then contact administrator
- Administrator can check CloudWatch logs:
/aws/lambda/alliance-risk-worker
Can't download PDF - 'Download link expired' error
Can't download PDF - 'Download link expired' error
Cause: Pre-signed S3 URLs expire after 1 hour for security.Solution:
- Navigate back to the Report page for the assessment
- Click Download PDF again to generate a fresh pre-signed URL
- Download within 1 hour of generating the link
Session expired / logged out unexpectedly
Session expired / logged out unexpectedly
Cause: JWT access token expired (default 60 minutes) and refresh token rotation failed.Solution:
- Log in again with your email and password
- Check Remember Me to extend session to 30 days
- If using multiple browser tabs, close inactive tabs to prevent token conflicts