SmartERP Documentation An Ashewa Technology Solutions Platform

The Ashewa AI Bridge and ORM Tool Calling

Technical architecture of the ashewa_ai_bridge, tool calling specifications, ORM model sandboxing, and security scopes.

1. Overview & Business Value#

This comprehensive operational guide details the architecture, business workflows, configuration parameters, and execution steps for The Ashewa AI Bridge and ORM Tool Calling within SmartERP.

Human-in-the-loop (HITL) AI governance workflow showing prompt reasoning, staging queues, managerial sign-off, and ORM execution.
SmartERP AI Copilot Human-in-the-Loop (HITL) governance and safety architecture.

AI Usage Metering and Copilot Orchestration

Technical architecture of the ashewa_ai_bridge, tool calling specifications, ORM model sandboxing, and security scopes.

2. Prerequisites & Security Access Groups#

  • Required Modules: ashewa_ai_workforce, ashewa_ai_bridge, smarterp_ai_agents
  • Security Groups:
    • AI Workforce Operator (Technical ID: ashewa_ai.group_ai_operator)
    • AI Systems Administrator (Technical ID: ashewa_ai.group_ai_admin)
    • Governance Officer (Technical ID: ashewa_ai.group_ai_governance)
  • Master Data Dependencies: Autonomous AI agent profiles, n8n orchestrator webhooks, LLM model parameters, prompt governance rules, and human-in-the-loop approval queues.

3. Step-by-Step Configuration & Execution#

Step 1: Navigating to the Interface#

  1. Log into your SmartERP instance at https://smarterp.et/odoo.
  2. Open the main App Switcher (grid icon in the top-left corner).
  3. Navigate to AI Workforce → Agents & Workflows.

AI Usage Metering and Copilot Orchestration

Step 2: Operational Data Parameters & Controls#

Ensure all mandatory parameters comply with enterprise operational standards:

  • Authorized Operator: Action executed under assigned RBAC permissions (AI Operations Architect, Automation Lead, Department Approver).
  • Relational Integrity: Linked to upstream master records, approval requests, or transactional ledgers.
  • Statutory & Quality Controls: Verified against Ethiopian statutory regulations and corporate governance standards.

Step 3: Operational Execution & State Progression#

  • State Progression Gate: Advance record from Draft through Audited to Confirmed / Certified.
  • Integrated System Impact: Automatically updates real-time operational states and posts financial/inventory journal moves.
  • Audit Verification: System registers tamper-evident audit records logging user ID, timestamp, and cryptographic transaction digests.

Architecture of the Ashewa AI Bridge#

The ashewa_ai_bridge is the core Python integration layer connecting large language model reasoning APIs with the SmartERP object-relational mapping (ORM) runtime.

Tool Calling Protocol#

SmartERP uses strict JSON Schema tool specifications compatible with standard LLM function calling conventions:

{
    "name": "reconcile_bank_statement_line",
    "description": "Matches a bank statement line to an open customer invoice or vendor bill.",
    "parameters": {
        "type": "object",
        "properties": {
            "statement_line_id": {"type": "integer", "description": "The ID of the account.bank.statement.line"},
            "invoice_id": {"type": "integer", "description": "The ID of the matching account.move"},
            "confidence": {"type": "number", "description": "Match confidence between 0.0 and 1.0"}
        },
        "required": ["statement_line_id", "invoice_id"]
    }
}

Security Sandboxing and Privilege Escalation Prevention#

  1. User Context Execution: AI tools execute strictly within the security context (self.env) of the initiating user, respecting all record-level rules (ir.rule) and access rights (ir.model.access).
  2. Read-Only vs Mutating Tools: Tools are partitioned into safe read-only queries (executed immediately) and mutating operations (staged into ashewa.ai.staging).

4. Advanced Configuration Points#

  • Automated Actions & Scheduled Tasks (Crons):
    • AI Bridge: Heartbeat check for n8n orchestrator nodes (ashewa_ai.ir_cron_heartbeat): Runs every 10 minutes to verify gateway connectivity
    • AI Governance: Auto-archive cleared approval queue tickets (ashewa_ai.ir_cron_archive_audit): Runs daily at midnight to maintain governance ledger performance
  • Custom Print Templates & Reports:
    • AI Agent Operational Execution Audit Trail
    • LLM Token Consumption & Cost Allocation Schedule
    • Human-in-the-Loop Decision & Override Ledger
    • Agent Workflow Error & Latency Analysis
  • Multi-Company Rules: Record-level security isolation under Company 1 (Ashewa Technology Solutions S.C.), preventing cross-company ledger leakage across parent and subsidiary legal entities.

5. Comprehensive Troubleshooting Matrix#

Error Symptom / ExceptionProbable Root CauseCorrective Action / Resolution
Connection Refused: n8n webhook unreachableEndpoint URL invalid, orchestrator service offline, or network firewall block.Check n8n service health and update bridge URL in AI Workforce Settings.
Token Limit Exceeded: Context window exhaustedPrompt context exceeds configured model maximum token threshold.Enable automatic context pruning and reduce historical message buffer in agent settings.
Governance Block: High-risk action requires human approvalAgent attempted financial posting or document deletion above autonomy threshold.Review and approve the pending transaction in the Human-in-the-Loop Governance Queue.
Last updated: 2026-11-15