Noetis Operations · Business engine
Business Process Analysis API
Diagnoses a documented business process.
Answers: "Can an engine find where a documented process loses time?" For operations managers.
Improvement ideas are hypotheses linked to your figures, not measured outcomes.
Available today
ImplementedImplemented: runs on the shared runtime with supplied material. One bounded development check on 2026-10-12 took 153s 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
- Process improvement plan linked to observed evidence.
- 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.
Why are invoice approvals slow and what should change?
Process: invoices arrive by email, AP clerk enters them (avg 2 days), department manager approves (avg 6 days, 30% need reminders), CFO approves all invoices over $5,000 (avg 4 days, CFO travels 2 weeks per month). 40% of invoices exceed $5,000. Late payment fees last quarter: $18,400. Two AP clerks, one on leave until June.
- Manager approval is the largest stated delay at 6 days
- CFO travel overlaps with approval of 40% of invoices
- Improvement hypothesis: raise or delegate the $5,000 threshold, to be tested
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), NVIDIA (NVIDIA). 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.
Process Mapper
Reconstruct steps, handoffs and dependencies.
Bottleneck Analyst
Identify delays and capacity constraints.
Exception Analyst
Examine failures and unusual cases.
Resource Analyst
Evaluate staffing and resource assumptions.
Improvement Planner
Propose measurable changes and monitoring.
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
- Staffing decisions about named individuals
- Uses only supplied material. No freshness guarantee beyond the documents provided.
- Required for every output during trials.
How to integrate
Send "engine": "operations" 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
- Business Decision Analysis API
- Supply Chain Risk Analysis Engine
- Reconciliation Evidence Review Engine
Content reviewed 2026-10-12 by the Encevra engine team. Engine version 0.1.0 on noetis-core-1.