Feedzai, a provider of AI-native financial crime prevention technology, has introduced Farol, an embedded AI agent designed to cut the time banks spend investigating fraud and to strengthen threat detection across their risk operations.
The release comes as the cost of tackling fraud rises across several fronts. Compulsory reimbursement requirements are widening banks’ exposure to losses, and spending on technology and manual reviews continues to grow.
Farol aims to ease that burden by working continuously alongside fraud teams, allowing them to handle more without expanding their resources. The agent sits inside Feedzai’s RiskOps Studio and offers conversational intelligence, automated analysis of rule performance and contextual case summaries, all within tools analysts already rely on.
According to Feedzai research, 68% of financial institutions are currently trialling agentic AI, yet most of these projects fail to deliver operational gains because external AI models are cut off from live transaction data. Farol tackles this disconnect by operating within established risk workflows, providing complete context, clear audit trails and the ability to act autonomously without disturbing core systems.
The agent arrives with several dedicated capabilities. Its Risk Strategy function examines rule sets to highlight practical insights, such as spotting rules that create noise without detecting fraud, and proposes tighter thresholds. This reduces rule maintenance from a task of days to one of minutes.
The Investigations function gathers and condenses alert data quickly, helping analysts resolve cases with more confidence, and has been shown to lower alert handling times by 20%. A Knowledge function acts as a built-in product specialist, answering questions about the platform without users needing to leave the interface. Farol also prepares Suspicious Activity Reports (SARs) up to 12 times faster by reducing the manual work of gathering and summarising information.
Farol extends Feedzai’s history of developing AI for financial crime prevention, which spans operational machine learning, explainable model outcomes, real-time cross-channel risk decisioning and federated network intelligence. The agent runs inside each institution’s own environment, meaning the data and insights it produces remain within the customer’s estate.
Feedzai chief product officer Pedro Barata said, “Fraud teams don’t need another tool to check; they need an agent that already knows their environment and the problems they want to solve.
“The Feedzai Farol agent puts actionable intelligence directly in the hands of the people fighting fraud every day. It surfaces the right information faster, takes repetitive work off their plate, and gives analysts the speed and confidence to act, so banks can focus on what matters, which is keeping their customers safe.”
Copyright © 2026 RegTech Analyst
Copyright © 2026 RegTech Analyst
