GAAP-tuned reasoning
Resolves accruals, coding, and PO mismatches with structured, tool-callable decisions.
Ledgr is the owned model core: a domain-tuned reasoning model that resolves AP/AR/close exceptions and a separate verifier model that gates every action before it touches the ledger.
Part of the Closora close
Ledgr is the owned model core: a domain-tuned reasoning model that resolves AP/AR/close exceptions and a separate verifier model that gates every action before it touches the ledger.
Every product in the suite shares memory, audit trail, and the verifier — composing one autonomous close function from owned models.
Resolves accruals, coding, and PO mismatches with structured, tool-callable decisions.
A separately trained model catches duplicate payments, wrong GL accounts, and policy breaches.
DPO/RLHF from controller overrides improves accuracy every month.
Smaller task models serve high-volume steps at a fraction of frontier cost.
Ledgr receives its inputs from your ERP, banks, or document stores in real time.
Owned, fine-tuned models make a structured, tool-callable decision with rationale.
An independent verifier gates the action against policy before anything is written.
The outcome and its provenance land in the immutable audit timeline.
| Training | NVIDIA NeMo on DGX |
|---|---|
| Serving | TensorRT-LLM + Triton |
| Verifier latency | <100ms per action |
| Moat | Proprietary close-cycle corpus |
Ledgr handles 3-way match exception resolution end to end, escalating only true exceptions.
Ledgr handles pre-write verification gate end to end, escalating only true exceptions.
Ledgr handles accrual and coding judgment end to end, escalating only true exceptions.
Ledgr included with the Growth platform.
Private fine-tune of Ledgr on your corpus.
GPU-served, layout-aware extraction for invoices, POs, and remittances.
View product →A realtime voice agent that runs AR collections calls autonomously.
View product →We'll run it in shadow mode against a recent period so you can compare.