Expense Policy Decision Engine (Starter)

This workshop introduces the starter version of the Expense Policy Decision Engine β€” a simple, document-driven GLIK agent that evaluates expense submissions against organizational policy thresholds.

The goal of this lesson is to give participants hands-on experience working with GLIK’s orchestration interface, memory objects, conditional logic, and agent-based decision routing. It is ideal for first-time users or teams exploring how GLIK can automate legacy, rules-based workflows.

Implementation Support & Expert Guidance

Need assistance deploying or customizing this GLIK template for your organization?

Our team offers dedicated coaching and technical walkthrough sessions to ensure successful adoption and alignment with enterprise requirements.

Typical areas of support include:

  • Template onboarding and orchestration strategy

  • Workflow configuration and logic review

  • Memory variable setup and session handling

  • Custom integration guidance (e.g. plugins, APIs)

πŸ” What This Agent Does

This GLIK agent automates the first stage of policy enforcement by evaluating uploaded expense documents (such as receipts or invoices) against preset business logic defined in a policy file. The agent can:

  • Ingest receipts (PDF/image)

  • Extract fields (amount, category, vendor, etc.)

  • Compare extracted values to rules from a policy document

  • Decide to approve, reject, or escalate based on thresholds or ambiguity

Sample Expense Report β€” This invoice will be used in the Starter template walkthrough to demonstrate how the GLIK agent evaluates policy compliance based on extracted data.

🧩 Key Components

Component
Function

Start Block

Accepts file uploads (receipts, invoices) and optional user notes

Doc Extractor

Parses uploaded documents into structured key-values

Data Enrichment

Normalizes formats and adds metadata (optional)

Variable Assigner

Stores parsed values in memory as invoice_data

IF/ELSE Logic

Compares values against the uploaded policy memory

LLM Block

Adds explanation or fallback reasoning if logic is unclear

End Block

Outputs a decision response (approve/reject/escalate)

πŸŽ“ Learning Outcome

By completing this lesson, participants will be able to:

  • Build and test a working GLIK agent using real invoice examples

  • Understand how file parsing and scoped memory interact in GLIK

  • Modify logic thresholds in the policy document to control agent behavior

  • Identify key escalation points and extend functionality in later versions


πŸ“ Practice Materials

You can use the following sample receipts and policy files to test the agent template.

Google Drive Folder: Access Example Files

Receipts and policy book samples are provided in the folder above. These materials are for testing purposes only and can be substituted with actual enterprise documents when ready.

Last updated

Was this helpful?