Skip to main content
Challenge

Build an SME Freight Invoice Discrepancy Queue and Carrier Correction Drafter

Reconcile logistics service provider freight invoices against contracted rate cards and demurrage rules. Isolate excessive fuel surcharges, detention penalties, and draft dispute correction notices.

Business OperationsHosted by Vera
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Reconcile logistics service provider freight invoices against contracted rate cards and demurrage rules. Isolate excessive fuel surcharges, detention penalties, and draft dispute correction notices.

SME Freight Procurement Specialist

Extract freight invoice lines, ocean bill numbers, and carrier detention charges from normalized PDFs.

Compare invoiced line items against agreed rate card limits and free-time allowance schedules.

Identify unjustified demurrage fees caused by terminal equipment downtime or customs hold delays.

Assemble an itemized invoice variance dossier and compile a formal carrier credit request draft.

A discrepancy queue showing disputed carrier charges, contract baseline comparison sliders, and one-click dispute letter generators.

Construct synthetic normalized freight invoice records and mock contractual rate cards in JSON format. Starter examples below are synthetic. They are not downloaded records.

Singapore open data API Adopt data.gov.sg dataset nomenclature and metadata structures to manage structured logistics rate cards.

semantic-kernel, pydantic, fastapi. Semantic Kernel facilitates pipeline chaining between numerical rate card audits and structured communication drafting. Local or hosted LLM with multi-step reasoning capabilities and JSON output format.

Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

Pinpoints demurrage charges assessed within agreed container free-time periods.

Calculates Singapore dollar rate card variance across local trucking and terminal surcharges.

Drafts carrier dispute emails detailing bill of lading numbers and contractual fee caps.

Prevents approval of invoices containing unexplained surcharges over 50 SGD.

```json [ { "input": { "invoice_id": "FRT-2025-101", "carrier_name": "Regional Feeder Lines", "bill_of_lading": "BL-77123", "ocean_freight_billed": 1200, "contracted_freight": 1200, "demurrage_billed": 450, "container_free_days": 5, "actual_dwell_days": 3 }, "expected_output": { "reconciliation_result": "dispute_required", "variance_amount": 450, "disputed_items": [ "Demurrage assessed for 3 days dwell when contract provides 5 free days" ], "proposed_credit_amount": 450, "dispute_letter_summary": "Carrier billed SGD 450 demurrage in error during free-time window." } }, { "input": { "invoice_id": "FRT-2025-102", "carrier_name": "Straits Trucking Pte Ltd", "bill_of_lading": "BL-88412", "ocean_freight_billed": 650, "contracted_freight": 650, "demurrage_billed": 0, "container_free_days": 3, "actual_dwell_days": 2 }, "expected_output": { "reconciliation_result": "cleared", "variance_amount": 0, "disputed_items": [], "proposed_credit_amount": 0, "dispute_letter_summary": null } } ] ```

Drafts dispute communications; financial credits and ledger modifications require human controller authorization. Use mock external writes. Require human review before any real deployment.

Rules

Participation guide

Drafts dispute communications; financial credits and ledger modifications require human controller authorization. Use mock external writes and human review.

Delivery guide

How work is evaluated

Evaluation

Pinpoints demurrage charges assessed within agreed container free-time periods. Calculates Singapore dollar rate card variance across local trucking and terminal surcharges. Drafts carrier dispute emails detailing bill of lading numbers and contractual fee caps. Prevents approval of invoices containing unexplained surcharges over 50 SGD.

Submission format

Runnable source, pinned dependencies, setup commands, working interface, example outputs, recorded demo, tests, and action logs.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
4 scoring checks
Binary
1 pass or fail dimensions
Ordinal
3 scaled dimensions
Dimension 1

Complete workflow

Extract freight invoice lines, ocean bill numbers, and carrier detention charges from normalized PDFs. Compare invoiced line items against agreed rate card limits and free-time allowance schedules. Identify unjustified demurrage fees caused by terminal equipment downtime or customs hold delays. Assemble an itemized invoice variance dossier and compile a formal carrier credit request draft.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 2

Correctness and evidence

Pinpoints demurrage charges assessed within agreed container free-time periods. Calculates Singapore dollar rate card variance across local trucking and terminal surcharges. Drafts carrier dispute emails detailing bill of lading numbers and contractual fee caps. Prevents approval of invoices containing unexplained surcharges over 50 SGD.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 3

Review interface

A discrepancy queue showing disputed carrier charges, contract baseline comparison sliders, and one-click dispute letter generators.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 4

Safe execution

Drafts dispute communications; financial credits and ledger modifications require human controller authorization.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Extract freight invoice lines, ocean bill numbers, and carrier detention charges from normalized PDFs.

  • Compare invoiced line items against agreed rate card limits and free-time allowance schedules.

  • Identify unjustified demurrage fees caused by terminal equipment downtime or customs hold delays.

  • Assemble an itemized invoice variance dossier and compile a formal carrier credit request draft.

Resources and assets

Reference links and supporting material

Dataset notes

Construct synthetic normalized freight invoice records and mock contractual rate cards in JSON format. Supplied starter examples are synthetic, not source extracts.

Challenge setup

Configuration summary for this challenge.

Challenge input

Input details are not configured.

Semantic Kernel

Agent Systems · Agent Frameworks

Evaluated output

No output checks are configured.

Evaluation checks
  • Extract freight invoice lines, ocean bill numbers, and carrier detention charges from normalized PDFs. Comp...
  • Pinpoints demurrage charges assessed within agreed container free-time periods. Calculates Singapore dollar...
  • A discrepancy queue showing disputed carrier charges, contract baseline comparison sliders, and one-click d...
Configured evaluation evidence
  • 2 public reference cases
Configured runtime
  • 1 configured tool

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Semantic Kernel · Optional

Evaluation contract

  • Complete workflow · Weight 40
  • Correctness and evidence · Weight 30
  • Review interface · Weight 20
  • Safe execution · Weight 10

Reference cases

  • 2 public reference cases

Workflow tasks

No workflow tasks are configured.

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build an SME Freight Invoice Discrepancy Queue and Carrier Correction Drafter