Automated PII Redaction & Cryptographic Parameter Tunneling

1. Overview & Technical Architecture#

For deployments utilizing hybrid cloud models (e.g., Claude or Gemini), SmartERP's PII Redaction Proxy sanitizes all prompt payloads prior to transmission.

1. Redaction Patterns & Substitution Tokens#

• TIN Numbers (10 Digits): Replaced with [TIN_MASKED_01].
• Bank Account Numbers (13-16 Digits): Replaced with [ACCT_MASKED_01].
• Employee Basic Salaries: Normalized to quartile relative ratios.
• National / Kebele ID: Replaced with [ID_MASKED_01].

Upon receiving the model's response, the reverse-tunneling engine re-hydrates the original identifiers strictly within the user's secure browser session.

2. Prerequisites & Infrastructure Requirements#

• Runtime Environment: Python 3.12+, PostgreSQL 16 with pgvector extension.
• Security Access Group: Ashewa AI / Administrator (Technical ID: muk_ai.group_ai_manager)
• Hardware Profile: Minimum 16 GB System RAM (CPU inference) or NVIDIA GPU with 8+ GB VRAM.

3. Step-by-Step Configuration & Verification#

Step 1: Navigating to Model Management#

1. Access your SmartERP instance at https://smarterp.et/odoo.
2. Open Settings → Technical → Ashewa AI → Model Registry.
3. Select the custom model profile.

{screenshot:70-pii-redaction-and-parameter-tunneling-step1-navigation}

Step 2: Testing Endpoint Health & Response Verification#

1. Click the Run Diagnostic Health Check button.
2. Verify token generation speed (tokens/sec) and latency benchmarks.
3. Review sample response in the diagnostic console.

{screenshot:70-pii-redaction-and-parameter-tunneling-step2-verification}

4. Advanced Configuration Points#

• Automated Tasks: muk_ai.ir_cron_model_health_monitor runs every 15 minutes.
• Multi-Tenant Boundaries: Custom model fine-tuning adapters are strictly segregated per tenant database.

5. Comprehensive Troubleshooting Matrix#