NOS handles 65% of supplier invoices end to end, with no operator

Invoice processing is a core operational workflow for NOS, spanning dozens of subsidiaries, suppliers, and systems. Before automation, every invoice depended on manual effort, with limited visibility into where the process was failing or how to improve it.

Manual, multi‑step invoice handling

Each invoice required operators to extract data, match it against purchase orders in SAP, validate business rules, and handle every exception by hand. With more than 20 fields to validate per invoice, this was slow, repetitive work that didn’t scale with volume.

Fragmented formats and entities

The workflow had to cope with multiple supplier systems, invoice formats, and business entities across the NOS group. Differences in structure and quality made it hard to standardise treatment and increased the risk of inconsistent handling.

No visibility into failure patterns

When mismatches occurred, operators investigated manually, often without clear visibility into why an invoice had failed or how frequently that pattern was appearing across the pipeline. There was no consolidated view of blocking reasons, no systematic way to prioritise exceptions, and no way to measure whether process changes were reducing failure rates over time.

DareData deployed GenOS Supervisor as the orchestration layer for the entire invoice treatment workflow.

Invoices are ingested automatically from the existing systems, with key fields extracted and normalised into a common structure. Business rules are applied to validate amounts, dates, suppliers, and other critical fields, and invoices are matched to purchase orders in SAP without operator involvement on the straightforward cases.

When a match is ambiguous, an inference step proposes the most likely candidate and routes the case to human review with full context attached: extracted fields, candidate POs, and the reasons for ambiguity. Operators no longer start from a blank screen; they confirm or correct a pre‑analysed suggestion.

For invoices the pipeline cannot resolve, the Supervisor surfaces a structured explanation of exactly why: missing data, rule violations, inconsistent references, or other blocking reasons. These explanations are aggregated into a consolidated view of failure patterns, allowing the team to see which issues occur most frequently and where process or data changes would have the biggest impact.

Throughout the pipeline, every step is logged and auditable inside the platform. The operations team can see how many invoices flowed straight through, how many required review, and how long each stage took, turning a previously opaque process into a measurable execution funnel.