Spectra automates KYC document review reducing analyst workload drastically
Spectra: A Rules-Driven LLM Pipeline for Automated KYC Document Processing
Artificial Intelligence
Summary
In financial markets, verifying a client's documents for compliance is slow because it involves many people and manual checks. The authors looked at this process and redesigned it to combine steps and reduce handoffs, making automation easier. They built Spectra, a system that uses rules and large language models to classify and extract information from documents accurately. Their system breaks tasks into clear steps tied to specific rules, improving accuracy and allowing easier audits. Spectra reduced human work by 96% while achieving nearly perfect classification and high extraction accuracy.
What this means in practice
- •For financial compliance teams: Automate classification and data extraction from KYC documents to speed onboarding and reduce manual reviews by analysts.
- •For legal tech developers: Build compliance checking tools that use rules combined with language models to validate documents against complex policies efficiently.
Authors
Miray Wahib, Ethan Tran, Rea Mourad, Mira Muti, Nikita Dvornik
Abstract
Know Your Client (KYC) onboarding in capital markets requires analysts to manually classify documents, extract structured data from heterogeneous sources, and validate compliance against complex regulatory policies. This process requires significant analyst time per client, with end-to-end onboarding often stretching to multiple weeks due to sequential handoffs. In this work, we analyze an on-boarding process and find that it comprises repeatable components well-suited to AI automation. We therefore propose a restructured workflow to be amenable to automation: we consolidate the traditional four-party process into two parties that share most of the work and can be automated together, eliminating intermediate handoffs that compound delays. To automate the remaining steps, we introduce Spectra, an AI-assisted document processing platform that combines a structured rules engine with LLM-based classification, extraction, and validation agents. The rules engine encodes compliance policy as a queryable database, enabling focused context injection that reduces token usage while improving extraction precision. Rather than a single monolithic prompt, the system decomposes document processing into isolated, auditable stages, each optimized independently and traceable to specific policy clauses. In evaluation on real KYC documents, Spectra achieves 100% classification accuracy and 89.4% extraction accuracy. Human review burden dropped by 96%.