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

# December 2025

It's here!

Colibri is now fully released as Conducttr’s licence for **self-paced exercises.** They're fast-to-build learning experiences that staff can complete independently without a facilitator. This release introduces a complete end-to-end workflow for authoring, publishing and analysing short scenario-based exercises.

## <mark style="background-color:$primary;">Improvements & New Features</mark> <a href="#improvements-and-new-features" id="improvements-and-new-features"></a>

### 1. Core Capabilities

#### AI-assisted exercise creation

Designers can auto-generate a complete first version of a Colibri exercise using **LISA**, by pasting a policy or procedure. The output is a fully formed quiz with data points, scoring, and personas, ready to refine or extend.

#### Self-paced scenarios

Colibri introduces a table-based scenario editor that looks like a MEL but progresses through **player actions rather than time**. Exercises are structured with **Chapters, Serials, Rows, and Steps**, giving designers a familiar organisational system while keeping the learner experience simple and focused.&#x20;

### 2. Scoring and Reporting

Colibri lets designers assign scores to each decision so that choices can be measured throughout.  AI-generated exercises automatically name datapoints for faster production but these can be renamed. Results are available in dedicated "colibri reports" that show completion, question-level performance, and where staff struggle.&#x20;

### 3. Registration, Personas, Style & Branding

All the usual Conducttr features remain

### 4. Mobile & Desktop Support

Exercises run smoothly across both mobile and desktop environments so that these small micro-simulations can be complete on the go


---

# 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://helpdocs.conducttr.com/colibri/release-notes-colibri/december-2025.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.