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’t configure it.
Two layers. One system.
Aura is the system. Aura Models are the intelligence behind it.
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
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 — 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 — 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’t 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
liveRewrite AI- or stiff-sounding drafts into natural, academic-quality prose.
Use this when you need drafts to read like a skilled human wrote them, especially student papers, reports, and long-form assignments. Aura Humanize runs a NeuraWrite-orchestrated pipeline (structure, vocabulary, voice, validation) so output is not locked to a single model fingerprint. Technical stages are summarized under Pipeline in Studio; day-to-day users just pick Humanize and choose strength in the product.
Humanize 2
previewNext-generation humanize profile, training on real approved edits from production.
Preview successor to Humanize 1. While the new fine-tune is finishing training, traffic may use a fast evaluation backbone under the same Aura humanize prompts. When the pair threshold is met, weights swap with no change to how you use the product.
Academic
Rigorous long-form drafting with citation discipline.
Academic
liveLong-form drafting that respects structure, discipline tone, and your sources.
Best for theses, journal-style sections, methods, literature reviews, and formal RFP language. Aura Academic uses a high-quality long-context backbone with NeuraWrite academic-voice prompts: it preserves citation markers, keeps section intent stable, and avoids casual or marketing tone where it does not belong.
Research
Web-grounded synthesis with claim-checking.
Research
liveGrounded answers with live web search, your knowledge base, and cited sources.
NeuraWrite’s answer-engine profile: it pulls fresh context from the web (e.g. via Tavily), merges in your uploaded or connected knowledge base, and synthesizes a single response with explicit source links, similar in spirit to consumer “ask with sources” products, but wired into your workspace, playbooks, and chat. A claim-check pass flags statements that are weakly supported so you can tighten wording before publishing.
Brand Voice
Style-guide adherence on every word you ship.
Brand Voice
liveOn-brand copy that follows your brand book, banned phrases, and tone rules.
Loads your active NeuraWrite brand book (voice, terminology, words to avoid, examples) into every request. Uses a low-temperature drafting profile so marketing, support, and social copy stay consistent without sounding generic.
Detect
In-house pre-predictor for AI-detection scoring.
Score
roadmapFast, cheap pre-check for AI-detection risk before you run full scans.
Roadmap: a small NeuraWrite classifier trained on labeled text vs. detector scores. When live, it will estimate risk so we only call expensive external detectors on borderline drafts, saving time and credits on obvious human-like output.
A typical Aura run
Intelligence in motion — not a chatbot.
What Aura does
- 1Aura is researching your topic…Calls Aura Research, runs a web search, deduplicates sources, claim-checks each one.
- 2Aura is drafting your section…Calls Aura Academic with your project's brand book and the verified sources.
- 3Aura is humanizing the draft…Calls Aura Humanize, scores against detection targets, retries if needed.
- 4Aura used Slack + Docs.Posts a summary to your project channel, drops the final doc into Drive, and waits for approval.
What Aura doesn’t do
- Ask you which model to use.
- Show raw provider names (“Claude” / “Llama”) 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.
Aura Humanize 2
Retrain on production-approved pairs. Higher GPTZero/Sapling targets.
Aura Score
In-house AI-detection classifier. Skip external scoring on obvious cases.
Aura Public API + MCP
REST and MCP server so customers can call Aura from inside their own agentic stacks.
Don’t 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.