> ## Documentation Index
> Fetch the complete documentation index at: https://developers.argosidentity.com/llms.txt
> Use this file to discover all available pages before exploring further.

# August 2026 update

> ARGOS Omni product update for August 2026

Hello from ARGOS Omni.

Here is what shipped in August.

***

## Grounds for every verdict

<span style={{backgroundColor: '#EEF4FF', color: '#0064FF', padding: '4px 12px', borderRadius: '16px', fontSize: '13px', fontWeight: '600'}}>New Feature</span>

An analysis result now gives you **more than values — it tells you why each value came out that way**. The Report tab shows the reasoning field by field.

<Frame caption="The Report tab — each field carries the reason behind its value.">
  <img src="https://mintcdn.com/argosidentity/OPYUfjaSdQpOBnpM/images/omni/en/analysis-report.png?fit=max&auto=format&n=OPYUfjaSdQpOBnpM&q=85&s=9b1f3e24f96a10a2374bf7da0aab962c" alt="Report tab" width="3756" height="1972" data-path="images/omni/en/analysis-report.png" />
</Frame>

Reasons are attached **per field, not per step**. When one step filled in several fields, each field gets its own reason. In the API, every leaf field arrives in an envelope with three keys — `value`, `reasoning`, and `sourceStep` — see [reading analysis results](/en/omni/guides/reading-analysis-results#the-extracteddata-envelope).

<Note>
  Analyses that completed before this feature existed have no reasoning, and it is not generated retroactively. "No reasoning provided" on screen **does not mean there were no grounds** — it means the reason could not be supplied.
</Note>

***

## Why a field came back empty

<span style={{backgroundColor: '#EEF4FF', color: '#0064FF', padding: '4px 12px', borderRadius: '16px', fontSize: '13px', fontWeight: '600'}}>New Feature</span>

A field defined in your output schema that received no value is now marked **not extracted** on the Report tab, together with **why it is empty**.

| Reason              | Meaning                                                         |
| ------------------- | --------------------------------------------------------------- |
| Parent missing      | The parent object was not produced, so the child was not either |
| Empty value         | The key exists but its value is empty                           |
| Not in final output | It was extracted but did not make it into the final result      |
| Tool error          | The responsible step's external engine call failed              |

This tells you whether to request a better document, fix the policy, or look at an engine problem. It also explains a low **Output Completeness** in the Analysis Score.

***

## Edit reference notes

<span style={{backgroundColor: '#EEF4FF', color: '#0064FF', padding: '4px 12px', borderRadius: '16px', fontSize: '13px', fontWeight: '600'}}>New Feature</span>

The **reference notes** attached to each action are now editable. Use **Edit Reference Notes** on the workflow edit screen, one entry per line.

<Frame caption="Edit Reference Notes — one line is one entry.">
  <img src="https://mintcdn.com/argosidentity/OPYUfjaSdQpOBnpM/images/omni/en/workflow-edit-reference-notes.png?fit=max&auto=format&n=OPYUfjaSdQpOBnpM&q=85&s=8ee9929017f748e3992055ca08fab8cd" alt="Edit Reference Notes" width="3736" height="1977" data-path="images/omni/en/workflow-edit-reference-notes.png" />
</Frame>

Changes apply without regenerating the playbook, so there is no 2–3 minute wait. Up to 20 entries per action, 500 characters each.

<Tip>
  When a verdict does not match your intent, check the reference notes before rewriting the policy. The cause is usually not the policy sentence itself but that sentence being carried into the action's reference notes incorrectly.
</Tip>

***

## Descriptions and metadata on folders and items

<span style={{backgroundColor: '#EEF4FF', color: '#0064FF', padding: '4px 12px', borderRadius: '16px', fontSize: '13px', fontWeight: '600'}}>New Feature</span>

Folders and items now take a **description and metadata** of their own. Attach an identifier from your system and it comes back unchanged as `metadata` in the API response.

***

## More AI models to choose from

<span style={{backgroundColor: '#F0FDF4', color: '#16A34A', padding: '4px 12px', borderRadius: '16px', fontSize: '13px', fontWeight: '600'}}>Feature Improvement</span>

**Four more AI models** are available at step 3 of workflow creation — [AI model and engines](/en/omni/dashboard/workflow-setup/engine-selection).

***

## Related pages

* [Reading analysis results](/en/omni/guides/reading-analysis-results) — the order to read a result in, and how to interpret it
* [Editing a workflow](/en/omni/dashboard/workflow-setup/editing-a-workflow) — reference notes, actions, and engines
* [Analysis results](/en/omni/dashboard/analysis-results) — reading the Report and Info tabs