AI agents for financial services customer operations
The open-source AI agent for company-wide work
Stage
Startup
Not given
Founded
2024
Not given
Based in
GB
Not given
Pricing model
Contact for pricing
Freemium
Pricing
Outcomes-based pricing model where customers pay only for successful query resolutions. Integration options include day 1 value on Intercom, Zendesk or Freshdesk, typically delivering 20-50% resolution rate for easiest queries, or more comprehensive integration achieving 80-90% handling time automat
Community (free): open-source self-hosted version with core agents, search, integrations, and community support. Business: $10/user/month billed annually, includes all core AI agent features, all integrations, SAML/OIDC single sign-on, priority email support, guided onboarding. Enterprise: custom pr
Key features
End-to-end dispute automation with evidence gathering and chargebacks
Collections agent for account arrears with personalized outreach
KYB automation with document verification and business checks
Insurance claims intake and processing
Customer service agent with conversation memory and action execution
Procedural agent controlled in plain language without coding
Built-in financial services compliance guardrails
Omnichannel support across phone, chat, email, SMS and social
Real-time monitoring and performance tracking
Multi-language support with same quality and compliance
Task execution across multiple tools
Permission-aware context retrieval
Support for commercial and self-hosted models
Hybrid search with BM25 and semantic search
Source citations for answers
Cost and token visibility by team and model
Code execution in sandboxed environments
25+ workplace connectors
Audit logs and compliance controls
What makes it different
Full operational depth covering back-office work that other AI agents avoid
Consistently higher CSAT than human teams with 98% customer satisfaction
No platform fees - pay only for successful query resolutions
Seamless integration with existing platforms without replatforming
Open source with Apache 2.0 license allowing inspection and self-hosting
Single unified system replacing multiple specialized tools
Model-independent context layer avoiding re-ingestion when switching providers
Full cost transparency and token tracking across all models
Flexible deployment with managed or self-hosted options