> For the complete documentation index, see [llms.txt](https://docs.glik.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.glik.ai/templates/policy-automation/overview/expense-policy-validator-summary-sheet.md).

# Expense Policy Validator — Summary Sheet

## Problem

Enterprises lose significant time and audit reliability when enforcing expense policies manually. Finance teams must cross-check receipts, approvals, and exceptions across disparate systems — often from static PDFs, Excel files, or HR portals. This leads to slow approvals, inconsistent enforcement, and non-compliant reimbursements.

<figure><img src="/files/LqDG40eaVWTHzjJIDeOj" alt=""><figcaption><p>This final segment of the workflow compiles and transmits the outcome of the expense validation process. After all checks and decision logic are executed, the system formats the result into a structured JSON payload (Build JSON Payload), including approval status, reasons, and escalation flags. The result is then delivered to an external system such as an ERP platform, audit log, or reimbursement portal (Submit to Expense System). The session is formally concluded with a closure block (Close Validation Session), ensuring clean termination and traceability.</p></figcaption></figure>

## Agent Architecture

**Input:**

* Uploaded receipt image or expense submission
* Optional: Attached policy document (`.pdf`, `.md`, `.csv`)

## **Processing Workflow**

1. **OCR Block** – Extracts data from receipt (vendor, amount, date, etc.)
2. **Variable Assigner** – Normalizes inputs (e.g., `expense_total`, `category`, `receipt_vendor`)
3. **Memory Retrieval Block** – Loads `policy_memory` for threshold values and blacklisted vendors
4. **Conditional Logic Block** – Checks thresholds, flags compliance issues
5. **LLM Block (Fallback)** – For ambiguous cases, generates escalation message
6. **Output Block** – Returns:
   * ✅ Approved
   * ❌ Rejected with reason
   * 🔁 Escalation suggested (if ambiguous)

<figure><img src="/files/D5C7zfI4m21xCmoCmxV3" alt=""><figcaption><p>This conditional branch handles expense reports that fall outside policy thresholds. The system first classifies the severity of the violation (Classify Violation Severity) and routes the case accordingly. If the violation is clear-cut, the workflow generates a rejection message with reasoning and audit trace metadata (Render Rejection Summary). If the violation is ambiguous or edge-case, it escalates the issue to a designated agent (Escalate to Policy Officer) who may trigger human-in-the-loop review or override logic. All escalation events are persistently logged (Log Escalation Event) for audit compliance and retrospective analysis.</p></figcaption></figure>

## Strategic Value

* **90%+ reduction in manual reviews** for standard expense categories
* **Audit-ready compliance trail** for finance teams
* **MCP-compatible JSON structure** for downstream integration with ERP or financial systems
* Deployable via **no-code GLIK Studio** or installable from the **GLIK Marketplace** (June 2025)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.glik.ai/templates/policy-automation/overview/expense-policy-validator-summary-sheet.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
