> For the complete documentation index, see [llms.txt](https://docs.unifize.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.unifize.com/release-notes/june-2025.md).

# June 2025

### Your Checklists are now smarter with Unifize AI

Unifize now supports an AI checklist field that generates structured data from context. This allows admins to embed AI-powered automation directly within checklists. With AI fields, teams can generate structured checklist data via unstructured data and emails with documents.

This capability allows organizations to reduce manual data entry, standardize process narratives, and optimize workflows in areas like quality management, audits, investigations, and supplier approvals.

{% embed url="<https://embed.wistia.com/deliveries/6e42b36811bb56d9a91d12831686e7b7.bin>" %}

### Feature capabilities

* AI is now a checklist field type available in Process Builder.
* Admins can configure how their specific AI works via the input and output fields to target checklist fields.
* To control the behaviour of your AI, Prompts can be configured via the settings of the AI Checklist field.
* AI generates structured data such as product details, dates, reasons, root causes, and corrective actions.
* AI output is editable by users before being saved, ensuring compliance and accuracy.
* Unifize AI can parse documents and attachments in emails and fill Checklist fields based on the same.
* AI suggestions are logged in the conversation window of every record to maintain traceability.

**How Unifize AI helps you**&#x20;

* Accelerate root cause investigations: AI surfaces likely root causes for defects, deviations, or customer complaints, drawing from your historical records to accelerate investigations.
* Refine corrective actions: When a non-conformance is logged, get AI-generated recommendations for corrective actions tailored to both internal processes and supplier relationships.
* Optimize asset maintenance: Let AI recommend asset-specific maintenance schedules based on usage history, manuals, and breakdown patterns, minimizing downtime with data-driven precision.
* Speed up ECOs: AI helps draft change justifications and impact summaries by analyzing linked specs, risk assessments, and prior change history, accelerating reviews and reducing rework.
* Draft risk justifications: Pull in relevant hazards, mitigations, and historical incidents to generate audit-ready rationales in seconds, whether you’re in design control, NC resolution, or CAPA planning.

**Note:** To get early access to Unifize AI for your organization, reach out to your customer success manager.

### Detailed Unifize AI guide

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><a href="https://docs.unifize.com/manage/processes/checklist/ai">Unifize AI admin guide</a></td><td>Complete guide to configure and work with AI checklist fields</td><td></td></tr><tr><td><a href="https://docs.unifize.com/user-guide/my-inbox/checklist/unifize-ai">Unifize AI user guide</a></td><td>End user guide for efficiently using Unifize AI in records</td><td></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.unifize.com/release-notes/june-2025.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.