Noetis Personal Decision · Personal engine for app builders
Personal Decision Engine for Apps
Helps one person weigh a decision against their own priorities and the facts they supply.
Answers: "Can an app help users compare options against their own priorities?" For individuals facing a significant personal choice.
Supports the user's own thinking. It does not give medical, legal or financial advice.
Available today
ImplementedImplemented: runs on the shared runtime with supplied material. One bounded development check on 2026-10-12 took 138.7s with 13 model calls and ended "incomplete". That is a development signal, not an evaluation. Customer access is by approved account.
What you send
- The decision
- Priorities and constraints
- Facts or notes the person supplies
- Text material up to 150,000 characters per run
What comes back
- Personalized decision brief with tradeoffs, untested beliefs and missing 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.
Should I accept the job offer in Denver?
Priorities: be near family (Chicago), grow in data science, save for a house. Offer: $118k, Denver, senior analyst. Current: $96k, Chicago, no promotion path stated. Rent in Denver estimate from a friend: $1,900; my Chicago rent: $1,500.
- Options compared with the user's stated priorities
- Facts the user supplied that favour each option
- What the user would need to find out to decide
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.
Goal Clarifier
Establish what the person is optimizing for, in their own words, and rank their stated priorities.
Options Analyst
Develop the realistic choices the material supports, including deferring or keeping the status quo.
Tradeoff Reviewer
Compare the consequences of each option against the stated priorities.
Assumption Challenger
Test the beliefs each option depends on and name the evidence that is missing.
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
- Medical, legal or financial advice
- Decisions about other people without their input
- Uses only supplied material. No freshness guarantee beyond the documents provided.
- Required for every output during trials.
How to integrate
Send "engine": "personal-decision" 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.