Aveni Intelligence
powers every Wealth
and Compliance product
It combines three tiers of AI models
with a compliance layer that checks every
result against UK regulation.
The right model at the right time
Each task goes to the tier that fits its complexity, speed and accuracy needs, automatically.
Tier 1 runs first
Every conversation is scanned in real time by lightweight classifiers before anything downstream is triggered.Tier 2 does the reasoning
FinLLM, Aveni’s own models, handles the specialist work: suitability, complaint handling, vulnerability, Consumer Duty analysis.Tier 3 handles the rest
General-purpose models take anything outside FinLLM’s specialism: general reasoning, creative drafting, edge cases.Fast, real-time compliance monitoring
Tier 1 models check every conversation as it happens, answering in about 0.2 seconds. It powers the high-volume monitoring inside Detect and Assure.
Detection Methods
FinLLM, built for UK financial services
FinLLM is Aveni’s own family of language models. It’s trained on a 100-billion-token corpus of real advice conversations, complaint journeys and compliance decisions built over seven years, alongside FCA rules and guidance. It handles the work that needs specialist judgement such as suitability, complaint handling, vulnerability, Consumer Duty.
FinLLM model suite – 6 sizes
General-purpose AI
For drafting, general reasoning and edge cases outside financial services, the engine uses leading models from OpenAI, Anthropic and Google. Their output passes through the same compliance checks as everything else.
Providers
Built for the reality of regulated financial services
See how the engine works inside Aveni’s Wealth and Compliance solutions.