Noetis Accounting · Business engine
Reconciliation Evidence Review Engine
Reviews reconciliation evidence and identifies exceptions.
Answers: "Can an engine review reconciliation workpapers and list exceptions?" For accounting and close teams.
Reviews supplied workpapers. It does not post entries, compute ledgers or replace an accountant's sign off.
Available today
ImplementedImplemented: runs on the shared runtime with supplied material. One bounded development check on 2026-10-12 took 132.4s with 15 model calls and ended "incomplete". That is a development signal, not an evaluation. Customer access is by approved account.
What you send
- Question
- Supplied text material
- Text material up to 150,000 characters per run
What comes back
- Reconciliation workpaper and exception report.
- Findings with the located quote and a support status from claim review
- Release status: released, incomplete with reasons, or failed
- Executed roles, usage and measured cost
Sample
Authored illustration. Written by Encevra to show the workflow. Not customer data and not a recorded model output.
Reconcile the bank statement against the ledger for May.
Bank: opening 10,000; deposits 5,200, 1,300; payments 2,450, 600; closing 13,450. Ledger: opening 10,000; receipts 5,200; payments 2,450, 600, 300 (cheque 1182); closing 11,850.
- Exceptions where the supplied entries do not match
- Evidence requests for unsupported adjustments
- Items to confirm with the preparer
The real response shape is documented in the API reference.
How the workflow operates
Each role is a responsibility in the workflow, served by a third party language model. More roles are not automatically better; depth and routing decide which run.
Built with
Models this engine uses: OpenAI (GPT), Anthropic (Claude). Specialists run on OpenAI models and the claim review and final brief on Anthropic models. If a provider has a temporary failure, the step can fall back to an OpenAI model, and the run records that.
Transaction Mapper
Normalize supplied ledgers and supporting records.
Reconciliation Analyst
Match balances and transactions.
Cutoff and Classification Reviewer
Flag potential period or category issues.
Exception Investigator
Trace unmatched items to available evidence.
Close Reviewer
Assemble unresolved items and review priorities.
Evidence and deployment
Evidence
This engine reads the text you send in the request. Each released finding carries the exact quote and its character span in that text, located mechanically before release. Quotes that cannot be located are labelled Insufficient evidence and never shown as source verified. Interpretation is reviewed as a separate step, and gaps such as a missing clause describe what was searched instead of citing text that is not there.
Deployment
Runs on Encevra hosted infrastructure using the third party models listed above. Every model call and fallback is checked against the deployment policy first. Private cloud and air-gapped deployment are planned; discuss deployment requirements.
What it does not handle
- Autonomous ledger posting
- Tax filing
- Spreadsheet and dataset execution is not available: Not built.
- Deterministic calculation is not available: Not built. Arithmetic is rebuilt by the model and checked by review only.
- Uses only supplied material. No freshness guarantee beyond the documents provided.
- Required for every output during trials.
How to integrate
Send "engine": "accounting" with your question and material from your server. Keys stay server side.
How to evaluate it
No published result for this workflow yet. Build a small answer key from your own work and compare against a strong single model baseline. See the evaluation checklist and method.
Cost and rights: pricing and licensing. Showing outputs to your own customers needs a written agreement.
Related engines
Content reviewed 2026-10-12 by the Encevra engine team. Engine version 0.1.0 on noetis-core-1.