Noetis Finance · Business engine
Financial Report Analysis Engine
Explains changes between financial reporting periods.
Answers: "Can an engine explain period changes in reports we supply?" For finance teams and controllers.
Narrative analysis of supplied reports. Exact calculation and spreadsheet execution are not implemented, so figures are restated from the material, not computed by a verified tool. Not investment advice or stock signals.
Available today
ImplementedImplemented: runs on the shared runtime with supplied material. One bounded development check on 2026-10-12 took 136.2s with 16 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
- Financial variance report with reproducible calculations and limitations.
- 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.
Explain the change in operating margin between Q1 and Q2.
Q1: revenue $1,200,000; cost of sales $720,000; operating expenses $300,000. Q2: revenue $1,320,000; cost of sales $830,000; operating expenses $310,000. Management note: "Margin improved due to pricing." Q2 included a one-off $40,000 freight surcharge in cost of sales.
- Gross margin moved from 40% to about 37% based on the supplied figures
- Management note claims margin improved; the supplied numbers do not support it
- Open question: what drove the rise in cost of sales
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.
Statement Normalizer
Map statements and align units, currencies and periods.
Calculation Analyst
Compute ratios and reconcile arithmetic through deterministic tools.
Performance Analyst
Examine revenue, expenses, margins and drivers.
Cash and Liquidity Analyst
Examine cash flow, working capital and financing needs.
Scenario Analyst
Test explicitly stated assumptions and sensitivities.
Financial Evidence Reviewer
Check explanations match the figures and disclosed evidence.
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
- Trading execution
- Personalized investment recommendations
- Deterministic calculation is not available: Not built. Arithmetic is rebuilt by the model and checked by review only.
- Spreadsheet and dataset execution is not available: Not built.
- Uses only supplied material. No freshness guarantee beyond the documents provided.
- Required for every output during trials.
How to integrate
Send "engine": "finance" 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
- Reconciliation Evidence Review Engine
- Business Data Analysis Engine
- Due Diligence Document Analysis API
Content reviewed 2026-10-12 by the Encevra engine team. Engine version 0.1.0 on noetis-core-1.