Noetis Writing and Communication · Personal engine for app builders
Writing and Communication Engine for Apps
Drafts a complete message in the person's voice with factual statements checked.
Answers: "Can an app draft complete messages from a brief and supplied facts?" For anyone writing an important message.
Uses the facts supplied and marks uncertainty. It does not send messages.
Available today
ImplementedImplemented: runs on the shared runtime with supplied material. One bounded development check on 2026-10-12 took 95s with 13 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
- Complete draft with verification notes.
- 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.
Draft an email to my landlord about the broken heater.
Heater broke 3 Nov. Reported by phone 4 Nov, no visit yet. Lease clause 9: landlord repairs essential services within 7 days. Tone: firm but polite. Want repair by Friday.
- A complete draft using only the supplied facts
- Points where the facts were uncertain, marked in the draft
- Tone notes against the brief
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.
Intent Clarifier
Identify purpose, audience and desired response.
Structure Editor
Organize the message for that audience.
Voice Editor
Follow the supplied tone and style preferences.
Claims Reviewer
Check each factual statement against supplied material.
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
- Sending messages
- Impersonating another person
- Uses only supplied material. No freshness guarantee beyond the documents provided.
- Required for every output during trials.
How to integrate
Send "engine": "writing" 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
- Personal Document Organizer Engine
- Campaign Brief Generation Engine
- Source-Based Learning Content Engine
Content reviewed 2026-10-12 by the Encevra engine team. Engine version 0.1.0 on noetis-core-1.