> For the complete documentation index, see [llms.txt](https://docs.uptiq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uptiq.ai/commercial-lending/release-notes/2026/september.md).

# September

Read the release notes for Commercial Lending version 2.6.17.0, released in September 2026.

September adds risk rating models, disposition approvals, packet ingestion, UCC lien search, and data repair tools.

### Risk rating models

* Build scoring models in a Model Library. Choose characteristics, set weights and scoring ranges, and map scores to grades.
* Import a model exported from another Model Library.
* Attach one model to a product type, and review ratings in a scorecard that ranks each result by points.

### Dispositions and approvals

* Define the reasons staff may cite when an application is declined or withdrawn. The reasons are shown to credit staff only, never to the applicant.
* Submit a close-out decision for approval. Approvers work from a Disposition Approvals queue that lists every close-out decision in the account.

### Packet ingestion

* Connect a Google Drive folder or an email inbox as a document source, then fetch new deal packets from it on the Packet Ingestion page. Document Source is a feature that an admin enables in **Settings** → **Features**.

### UCC and liens

* Search a business for UCC, state tax, and federal tax liens, and review each lien. UCC Search is a feature that an admin enables in **Settings** → **Features**. It is off by default.

### Agents

* Open the chat agents on the Agents page, and export a chat as Markdown.

### Financial review

* Add manual adjustments with an optional reason that tells a reviewer what the adjustment is about.

### Administration

* Clone a product into other companies.
* Repair Schedule C and Form 8825 data from earlier versions, with a dry run before you apply the repair.

***

{% columns %}
{% column width="83.33333333333334%" %}

<p align="right"><em>Maintained by</em> <mark style="color:green;">Abhishek Paul</mark><br><code>AI-assisted, human-approved</code></p>
{% endcolumn %}

{% column width="16.666666666666664%" %}

<div align="left"><img src="https://2424445642-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FoNOfYlgbuwiWKkdQsRIp%2Fuploads%2Fgit-blob-d034645b4f8f8ee661985f5306b60ded3289653c%2Fmaintainer-abhishek-paul.png?alt=media" alt="" width="60"></div>
{% endcolumn %}
{% endcolumns %}


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.uptiq.ai/commercial-lending/release-notes/2026/september.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
