The loan origination system where
loan officers
and AI agents
work together

Sphera Credit is an AI-native loan origination system for lenders. It combines a white-labeled borrower portal, a decision engine, automated loan processing, AI document collection and integrations with an AI Agent Studio, where the lender's own team builds, tests and deploys AI agents. Loan officers and underwriters supervise the agents' work and keep every credit decision.

Sphera Credit is built for lenders in Canada and the United States whose origination, underwriting, monitoring or servicing still involves manual work: credit unions, banks, non-bank lenders, private and hard money lenders, commercial real estate lenders and high-volume mortgage brokerages. Products that are already fully automated, such as credit cards, are a weaker fit.

Sphera Credit supports loan types that still need hands-on underwriting. That includes first and second mortgages, DSCR, bridge, fix-and-flip and new construction loans, commercial real estate loans on multifamily (CMHC-insured, FHA-insured or conventional), office and industrial properties, small business loans and lines of credit, and unsecured consumer loans.

Sphera Credit is a loan origination system, so its AI agents work inside the lending workflow itself. They request and read borrower documents, cross-check the data, calculate ratios, update the lender's systems and draft the credit memo, each within permissions the lender sets, and every run is recorded step by step. Credit policy runs as deterministic decision flows, so the same file always gets the same decision. Lenders also choose where AI processing happens: Canadian clients can keep prompts and AI responses in Montreal, while a general-purpose assistant may process a prompt in a data centre outside Canada.

Sphera Credit encrypts client data in transit and at rest, and limits access with role-based permissions, row-level security, single sign-on and multi-factor authentication. Client data is never used to train AI models, and the AI provider is contractually barred from doing so. Clients can also have their prompts encrypted, with keys managed by Sphera Credit or keys they manage themselves.

For Canadian clients, Sphera Credit stores client data in data centres in Montreal and runs AI inference in Montreal as well, so prompts, documents and AI responses stay in Canada. For US clients, Sphera Credit stores client data in data centres in the United States and runs AI inference there as well, so prompts, documents and AI responses stay in the United States. Every client can choose the region where its AI inference runs. Sphera Credit follows PIPEDA and the private-sector privacy laws of Quebec (Law 25), Alberta and British Columbia.

Sphera Credit pricing is tailored to each lender and has two parts: an implementation fee and an ongoing platform fee. The implementation fee depends on the scope of the rollout, because Sphera Credit's team works alongside the lender on both the technical setup and change management. The platform fee is outcome-based: it follows the loan volume processed on the platform, so it scales with the size of the lender's operations.

No. Sphera Credit can run origination end to end as the lender's loan origination system, or its AI agents can work on top of the LOS, CRM and data providers the lender already uses, reading from those systems and writing updates back to the same records. Sphera Credit supports both paths and recommends the first to lenders who are ready to redesign how the work gets done.

Sphera Credit's view is that replacing the LOS is the stronger long-term choice. Systems built before generative and agentic AI were never designed for AI agents to work in them, so adding AI on top of them tends to be a short-term fix. A technology shift of this size normally changes how work gets done and how business processes are designed. Replacing the LOS is a deeper organizational change, which is why Sphera Credit's white-glove implementation covers the technology, the change management and the redesign of business processes together.

No. The lender's credit policy runs as decision flows that its own credit team writes, tests and versions, built on deterministic rules and, where the lender chooses, machine learning models. Files that fall outside the credit box are routed to the lender's underwriters or to AI agents that gather and analyze more information. Agents prepare the file, the lender's team makes the decision, and every step is recorded in an audit trail.

Sphera Credit was founded by Joseph Edelmann (CEO) and Uriel Manseau (CTO) and is based in Toronto. Joseph Edelmann studied finance at McGill University and built the underwriting system at Passage, where he underwrote more than 1,000 international student loans. Uriel Manseau holds a bachelor's degree in industrial engineering and a master's in applied mathematics, and previously led growth at Billdr.