The intelligence layer behind NeuraWrite

The platform.
The system that runs everything.

NeuraWrite is the orchestration layer behind every workflow. It decides what to do, calls the right tools, picks the right model, remembers context across runs, and learns from every result. You experience the platform. You don\u2019t configure it.

4
Models live
1
In preview
1
On the roadmap
0
Pairs toward next retrain
captured in production

Two layers. One system.

Aura is the system. Aura Models are the intelligence behind it.

The system layer

Aura

  • Orchestration — plans, executes, and resumes every workflow step
  • Memory — carries context across runs, projects, and connectors
  • Tool routing — picks the right connector for the job (Slack, Docs, web)
  • Evaluation — scores its own work and learns from every result
  • Governance — wraps every call in your project policies and audit log
The model layer

Aura Models

  • A multi-model intelligence layer Aura calls in real time
  • Specialized profiles per capability — humanize, draft, research, brand voice, score
  • Automatic fallback when a provider degrades
  • Trained or tuned by NeuraWrite — every run feeds the next retrain
  • Never selected by users — Aura picks the right one

How Aura works

Aura turns intent into action across your tools and data.

Decide

Aura plans the next step. It chooses which Aura Model to call, which connector to use, and what to retrieve from memory.

Execute

Aura runs each step \u2014 calls the model, invokes the tool, updates the document, captures the result. Every action is observable.

Explain

Aura emits structured events. The runtime UI renders them as Activity, Trace, and Document updates \u2014 so you see exactly what Aura did and why.

Remember

Aura persists context, sources, brand books, and prior decisions. Every workflow inherits everything Aura has learned about your work.

Adapt

When a provider degrades or a connector fails, Aura falls back automatically and explains the change. Workflows don\u2019t break.

Govern

Every Aura call runs inside your project policies, guardrails, and audit log. Aura is intelligent and accountable.

Aura Models

One name. One brand. A model for every job.

Aura Models is the multi-model intelligence layer Aura draws on. You never pick a model. Aura routes every step to the profile best suited for it, with deterministic fallbacks.

Humanize

Pass every detector while keeping every citation.

Humanize

live

A multi-stage humanization pipeline tuned for academic prose.

Aura Humanize is not a single model — it is an orchestrated pipeline. Each stage targets a different detector fingerprint: structural (Claude), lexical (DeepSeek), opener distribution (Llama), local validation, and a final perplexity pass via our humanization closer. The result is text that matches no single model fingerprint, which is the core reason multi-detector evasion works.

GPTZero target
≥ 85
Sapling target
≥ 85
Pipeline stages
3 always-on, 2 conditional
Training pairs (humanizer-tune)
199 (v1)
Available on pro · business · enterprise

Humanize 2

preview

Next humanization retrain — capturing approved production pairs now.

Successor to Aura Humanize 1, retrained on 500+ approved production pairs from the live capture loop. Triggered automatically once the training-pair threshold is reached.

Pairs collected
live counter on /aura
Threshold to ship
500 approved pairs
Available on pro · business · enterprise

Academic

Rigorous long-form drafting with citation discipline.

Academic

live

Citation-aware academic drafting. Tuned for theses, journals, RFPs.

A Sonnet-backed Aura profile with a NeuraWrite academic-voice system prompt and structural-anchor enforcement. Used for long-form drafting where citations, methodology, and discipline-specific tone matter.

Avg paper length
4–8k words
Citation preservation
100%
Available on pro · business · enterprise

Research

Web-grounded synthesis with claim-checking.

Research

live

Web-grounded multi-source synthesis with claim-checking.

An Opus-class profile that combines Tavily web search, knowledge-base retrieval, and a NeuraWrite claim-check pass. Outputs include source attribution and confidence scoring.

Source attribution
every claim
Claim-check
auto
Available on business · enterprise

Brand Voice

Style-guide adherence on every word you ship.

Brand Voice

live

Style-guide-aware drafting from your brand book.

A low-temperature Sonnet profile that loads your active brand book (voice rules, banned phrases, style guide) into the system prompt. Used everywhere brand consistency matters: SEO posts, social, customer-facing copy.

Voice adherence
auto-evaluated
Banned-phrase enforcement
pre + post
Available on pro · business · enterprise

Detect

In-house pre-predictor for AI-detection scoring.

Score

roadmap

In-house AI-detection pre-predictor. Cheaper than external scoring.

A small classifier we are training on labeled (text, gptzero_score) pairs. Predicts AI-detection score before calling an external API, so we only spend on borderline content.

Target accuracy vs GPTZero
≥ 90%
Inference cost
~$0.0001 / call
Available on business · enterprise

A typical Aura run

Intelligence in motion \u2014 not a chatbot.

What Aura does

  • 1
    Aura is researching your topic\u2026
    Calls Aura Research, runs a web search, deduplicates sources, claim-checks each one.
  • 2
    Aura is drafting your section\u2026
    Calls Aura Academic with your project's brand book and the verified sources.
  • 3
    Aura is humanizing the draft\u2026
    Calls Aura Humanize, scores against detection targets, retries if needed.
  • 4
    Aura used Slack + Docs.
    Posts a summary to your project channel, drops the final doc into Drive, and waits for approval.

What Aura doesn\u2019t do

  • Ask you which model to use.
  • Show raw provider names (\u201cClaude\u201d / \u201cLlama\u201d) in the UI.
  • Make you copy-paste between tools.
  • Forget what you set up last week.
  • Break when one provider has an outage.

Aura roadmap

Coming next.

Triggers at 500 approved pairs

Aura Humanize 2

Retrain on production-approved pairs. Higher GPTZero/Sapling targets.

Q3 2026

Aura Score

In-house AI-detection classifier. Skip external scoring on obvious cases.

Enterprise GA

Aura Public API + MCP

REST and MCP server so customers can call Aura from inside their own agentic stacks.

Don\u2019t buy a chatbot.
Buy a system that ships work.

Aura is the orchestration brain behind NeuraWrite. Talk to us about running it on your enterprise content, with your tools, under your governance.