Noetis Policy · Business engine

Public Policy Comparison Engine

Compares public policy proposals against explicit evaluation criteria.

Answers: "Can an engine compare policy proposals against explicit criteria?" For policy analysts.

Separates factual findings from value judgments and does not take a political position.

Configure in Studio Request an evaluation Test engine (sign in)

Available today

Implemented

Implemented: runs on the shared runtime with supplied material. One bounded development check on 2026-10-12 took 158.6s 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

Sourced policy comparison separating factual findings from value judgments.
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.

Compare these two proposals for reducing city traffic congestion against the council criteria.

Criteria: reduce peak congestion, cost under $20M, equity for low-income residents. Proposal 1: congestion charge of $8/day in the centre. Projected 15% traffic drop citing London's 2003 scheme. Revenue $12M/year. No discount for low-income drivers. Proposal 2: expand bus lanes and frequency. Cost $26M. Claims 10% traffic drop; no source given. Bus riders are 60% low-income per 2022 city survey.

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), SpaceXSI (Grok). 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.

Proposal Analyst

Extract mechanisms, scope and implementation details.

Evidence Analyst

Review supporting research and its limitations.

Stakeholder Analyst

Map documented impacts on affected groups.

Fiscal and Implementation Analyst

Check resource assumptions and feasibility.

Tradeoff Reviewer

Examine competing objectives and uncertainties.

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

Advocacy or campaigning
Uses only supplied material. No freshness guarantee beyond the documents provided.
Required for every output during trials.

How to integrate

Send "engine": "policy" 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.

Schedule an engine setup call

Related engines

Content reviewed 2026-10-12 by the Encevra engine team. Engine version 0.1.0 on noetis-core-1.