> For the complete documentation index, see [llms.txt](https://help.tillit.cloud/tillit/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.tillit.cloud/tillit/tools/aura.md).

# Aura

## Aura - Autonomous Reasoning Agent

Aura is a continuous discovery engine for manufacturing operations. It connects to your existing data systems, runs autonomous investigations on a scheduled cycle, and delivers structured findings without requiring a dedicated data science team to operate it.

## What problem it solves

> *The answers your plants need are already in your data. Nobody has the time to find them.*

Manufacturing plants generate millions of events and data points every shift. The bottleneck is rarely the data itself, it's the time and expertise required to find patterns across disparate systems. Useful insights go unnoticed because no one has capacity to look for them consistently.

Aura runs that analysis automatically, surfacing findings across operations, maintenance, quality, planning, and supply chain perspectives on every cycle.

<figure><img src="/files/kUFc8XTsmHaXxeKClf37" alt=""><figcaption></figcaption></figure>

## Data sources

Aura connects to the four systems most manufacturing operations already run on. It reads their schemas directly, no migration or replacement required.

<table><thead><tr><th width="146.71484375">System</th><th>Full name</th><th>What it covers</th></tr></thead><tbody><tr><td>IBP / ERP</td><td>Supply chain planning</td><td>Forecast misses, broken plan assumptions</td></tr><tr><td>WMS</td><td>Warehouse management system</td><td>Inventory levels, stalled SKUs</td></tr><tr><td>MES</td><td>Manufacturing execution system (such as TilliT)!</td><td>Downtime, scrap, performance loss by asset and shift</td></tr><tr><td>PLM</td><td>Product lifecycle management</td><td>Rejects and rework by product variant</td></tr></tbody></table>

##

***

### Feedback and learning

After reviewing a finding, users can leave structured feedback. Aura asks two questions:

* Is this factual?
  * Did you already know about this?

The answers, along with any free-text comments, are passed to the agents as context in subsequent cycles. Over time, this helps Aura focus on findings that are both accurate and novel for your team.

***

### Security and permissions

Aura does not introduce a new security perimeter. It runs inside your existing tenant using role-based authentication (RoIAM) in your chosen region — US, EU, or AU. Data and agents remain within a contained environment.

Four capability areas are managed separately through the admin panel, each with read and write scope:

| Capability           | Read | Write |
| -------------------- | ---- | ----- |
| Board findings       | ✓    | ✓     |
| Cycles               | ✓    | ✓     |
| Settings             | ✓    | ✓     |
| Feedback and reports | ✓    | —     |

Feedback and report capabilities are scoped separately from board and cycle management.