Use Case Intelligence RSS Search use cases Search
AWS Agriculture Basel, Switzerland Company newsroom

Syngenta

Document Processing · Risk Management

Syngenta needed to handle supplier invoice tax processing in Argentina despite multiple provincial taxes, exemptions, and dual SAP systems, where manual entry slowed operations, introduced errors, and increased compliance risk.

Read the original story Explore all use cases
More than 90% accuracy in tax bookings

Reported impact

Business outcome

Syngenta achieved more than 90% tax-booking accuracy while reducing manual errors and speeding tax processing, improving data quality and audit readiness, and creating a modular platform that can be extended across LATAM and into additional compliance workflows.

  • Compliance
  • Productivity Improvement
  • Risk Reduction
  • Scalability

Solution

DXC built Syngenta an intelligent tax automation solution on AWS-native services to process supplier invoices for Argentina. Optical Character Recognition (OCR) reads and digitizes invoice content, and GenAI capabilities analyze the extracted tax information at scale so it can be matched across multiple systems, including Syngenta’s dual SAP environment. The processed data is consolidated in Syngenta’s GenAI Invoice Data Lake, which the story describes as a central platform connecting OCR, AI, and analytics capabilities for continuous learning and improvement. Interactive dashboards sit on top of this flow to give tax experts real-time visibility into issues, enriched data, and faster correction workflows. The implementation is modular, receives weekly updates, and is designed to extend to other LATAM countries while also supporting new applications for SAP tax entry improvement and regulatory-change summarization.

Data flow

Supplier invoices are ingested through OCR, digitized, and passed to GenAI-based analysis running on AWS-native services. The resulting tax data is matched across Syngenta’s dual SAP systems and consolidated in the GenAI Invoice Data Lake, where AI and analytics support continuous improvement. Interactive dashboards then surface real-time insights to tax experts for review and correction.

Solution architecture

6 components · 5 layers
  1. Ingest
    • Optical Character Recognition (OCR) Automatically reads and digitizes supplier invoice data for downstream tax analysis.
  2. Compute
    • AWS-native services Provide the cloud foundation on which the intelligent tax automation solution is built.
    • GenAI capabilities Analyze digitized invoice and tax data at scale to improve tax booking and automation outcomes.
  3. Storage
    • GenAI Invoice Data Lake Acts as the central platform connecting OCR, AI, and analytics capabilities for continuous learning and a unified invoice and tax view.
  4. Serving
    • interactive dashboards Present real-time insights so tax experts can identify and correct issues faster.
  5. Uncategorized
    • SAP Serves as the enterprise system environment whose dual instances are matched against invoice tax data and targeted for improved tax entry.

Architecture clues

  • Deployment targets tax processing for Argentina while Syngenta is headquartered in Basel, Switzerland.
  • The architecture is modular and receives weekly updates.
  • The platform is designed to extend to other countries across LATAM.
  • The solution matches invoice tax data across dual SAP systems.
  • Two new applications are already in development: one for SAP tax entry improvement and another for summarizing and tracking regulatory changes.

Evidence from the source

"Improved data quality and audit readiness"
"More than 90% accuracy in tax bookings"
"This modular solution forms the foundation of Syngenta’s GenAI Invoice Data Lake, a central platform that connects OCR, AI and analytics capabilities to deliver continuous learning and improvement."
"built on AWS-native services, combines Optical Character Recognition (OCR) with GenAI capabilities to automatically read and digitize invoice data, then analyze it at scale."
"extracts tax data from invoices, matches it across multiple systems and displays real-time insights through interactive dashboards."
"multiple provincial taxes, exemptions and dual SAP systems made supplier invoice processing highly complex. Manual entry slowed operations and increased compliance risk."
Transparency Evidence & methodology 90/100 reference value · 94% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value90/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact15/25
    1 metric describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence94%
  • Source authority25/25
    The deployment is described by the adopting organization or a government source.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    6 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Syngenta

    Syngenta customer story

    First-party
    https://dxc.com/insights/customer-stories/syngenta-achieves-tax-accuracy-with-genai-powered-automation
    Source type
    Customer-published story
    Published
    Nov 20, 2025
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Nov 20, 2025 · DXC Technology · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
AWS Nov 14, 2024 Reveleer Healthcare United States To address these challenges, Reveleer is using Amazon Web Services (AWS) technologies. Value-based care is a healthcare model that prioritizes quality over quantity, focusing on improving patient outcomes and reducing… The Reveleer platform has a 100 percent uptime, and 90 percent of responses are served in under 8 seconds.… Document ProcessingRisk Management Amazon Bedrock · Amazon Comprehend Medical AWS Oct 1, 2024 Intact Financial Corporation Financial Services Canada It could significantly improve agent efficiency by off-loading repetitive issues to a chatbot and automatically notifying a supervisor when a challenging interaction required assistance. The company sought to build a… 10% calls automatically transcribed within 4–6 hours Document ProcessingRisk Management Amazon Transcribe AWS Sep 11, 2024 Georgia-Pacific Manufacturing Atlanta The lack of a centralized, readily accessible knowledge base often leads to reduced machine productivity, prolonged machine downtime, and higher troubleshooting and repair costs. Making phone calls to experts and… Accelerated operator onboarding Customer Service AutomationDocument Processing Amazon Bedrock · Amazon Kinesis