SAS: Using AI Agents to Revolutionise Fraud Detection

The Silicon Valley race accelerating the AI industry is widening a critical gap in sector-specific expertise.

As organisations work to scale AI agents and models across financial services, SAS is rolling out a suite of purpose-built solutions designed to tackle industry-specific challenges.

This expansion forms part of its US$1bn investment in industry solutions, with plans to strengthen its portfolio of accelerators through 2026 in response to growing market demand.

Manisha Khanna, Global Market Strategy Lead, Applied AI at SAS, says: “When organisations are left stitching together ad-hoc AI frameworks and experiments, they often fail to achieve the competitive edge they’re looking for when they invest in AI”.

Streamlining global supply chains

Leading the charge in accelerating operational intelligence is the SAS Supply Chain Agent.

It streamlines supply and operations planning (S&OP), a critical process retailers and manufacturers use to manage inventory.

Traditional S&OP is a demanding multi-day process that relies on complex spreadsheets to forecast inventory needs over the coming year.

Because of the time and resources involved, most organisations only run this planning process once a month.

SAS’ new agent steps in by continuously balancing demand and operations, helping users optimise supply chains in near real time.

Business users can interact with the agent through a chat interface to explore multiple scenarios and likely outcomes, including what might happen if demand drops by 15%.

The Supply Chain Agent also explains how it reached specific decisions, helping to strengthen transparency and trustworthiness.

Kathy Lange, Research Director at IDC’s AI, Data and Automation Software practice, says: “Current pre-packaged agents tend to tackle basic processes – with Supply Chain Agent, SAS is compressing a very complex process, which could deliver significant value.

“This offering positions SAS to bring its longstanding supply chain knowledge to a new generation of agentic AI solutions.”

Transforming operations and safeguarding workers

Leading the charge in accelerating operational intelligence is the SAS Supply Chain Agent.

It streamlines supply and operations planning (S&OP), a critical process retailers and manufacturers use to manage inventory.

Traditional S&OP is a demanding multi-day process that relies on complex spreadsheets to forecast inventory needs over the coming year.

Because of the time and resources involved, most organisations only run this planning process once a month.

SAS’ new agent steps in by continuously balancing demand and operations, helping users optimise supply chains in near real time.

Business users can interact with the agent through a chat interface to explore multiple scenarios and likely outcomes, including what might happen if demand drops by 15%.

The Supply Chain Agent also explains how it reached specific decisions, helping to strengthen transparency and trustworthiness.

SAS Worker Safety harnesses synthetic data and digital twins to train computer vision models on rare but plausible hazardous workplace incidents in financial operations centres and back-office environments.

Data from between 2024 and 2025 showed 124 workers fatally injured in the UK, with falls from height and machinery accidents accounting for a significant share of these incidents.

The new solution generates realistic training footage for computer vision models targeting specific workplace safety scenarios, enabling organisations to simulate forklift collisions or equipment failures without risking actual staff.

Using synthetic data also eliminates exposure of personally identifiable information during model training, supporting compliance in regulated fintech settings.

Fighting fraud across financial services

To address rising financial fraud, SAS is launching Fraud Decisioning for Payments to enable real-time fraud detection across payment transactions and digital banking channels.

A SAS study with the Association of Certified Fraud Professionals found that 75% of anti-fraud professionals report surging financial fraud and scams targeting consumers.

Additionally, 55% expect significant rises in deepfake social engineering and Gen AI document fraud over the next two years.

Against this escalating threat, global banks, insurers and financial services organisations are turning to SAS for its advanced fraud detection models.

These agents safeguard consumer assets and identities across the financial services ecosystem.

The Fraud Decisioning for Payments models draw on patterns from a broad dataset contributed via consortium by major global financial institutions, covering credit card, debit card and ATM fraud.

These models also tackle digital wallet fraud and emerging threats like money mule detection, enabling institutions to deploy sophisticated capabilities without starting from scratch on the SAS platform.

By delivering accelerators tailored for specific functions that integrate seamlessly with existing workflows, SAS bridges the divide between experimentation and real-world deployment in financial services.