> For the complete documentation index, see [llms.txt](https://docs.ins-pi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ins-pi.com/command/features/command-dialog.md).
# Command Dialog (AI assistant)
Command Dialog is the assistant built into Command; it answers portfolio questions with graded evidence, builds content for you and writes only after you confirm.
**Command Dialog** is the assistant built into YouDesign Command. You type a question or a request in plain words, and it answers from the records in your ServiceNow instance, shows how much the answer can be trusted, and opens the content it builds in a tab. Its language processing runs in your browser, and it never sends your data to a third-party AI service.
## What it is
A panel on the right of the screen. Its header reads **ins-pi Transformation OS™**, with **Reset thread** and **Close panel** buttons. Below the conversation is the message box.
The Command Dialog with an answer and the attached-content chip
What you can ask today:
| You want to | Try | What happens |
| ----------------------------------- | --------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
| Learn a term | `what is a SWOT?`, `measure vs score` | A short explanation and a chip to create one. |
| Find retirement candidates | `which applications should we decommission?` | A ranked shortlist, with chips to show it as a TIME Analysis or on a Roadmap, and to ask about one of the applications. |
| Find where to invest | `where should we invest first?` | A ranked shortlist. |
| Get a recommendation for one record | `should we retire PayGate?` | An [Advisory Report](#the-advisory-report) opens in a tab. |
| See dependencies | `what depends on PayGate?` | A view of what depends on that record. |
| Check portfolio health | `summarize the application portfolio` | A live overview dashboard opens. |
| Build a dashboard | `create a CFO dashboard` | A preview, then **Yes, create it**. |
| Create a lifecycle | `create a market lifecycle with phases idea, launch, growth, retire for products` | A preview, then **Yes, create it**. |
| Plan a cost reduction | `how can we reduce cost by 25% by end of this year?` | A guided **Cost reduction assessment** in the conversation. |
| See strategic goals | `what are our strategic goals?` | A summary of goals and how they are tracking. |
| Check alignment | `which applications support the business capabilities?` | A coverage answer. |
| Find missing data | `which data is missing for business applications I own?` | A list of gaps. |
| Understand what is on screen | `explain this roadmap`, `what are we looking at?` | A summary of the open content. |
| Create content | `create a roadmap`, `create a SWOT` | The content opens straight away. |
| Take the tour | `give me a demo` | A guided walkthrough. |
## When to use it
* You have a portfolio question and want an answer with its evidence, not a spreadsheet.
* You want a starting point built for you, such as a dashboard, a lifecycle or a shortlist, and then refine it by hand.
* You want to understand or explain the content you have open.
## How to
### Open it and ask
1. Click **Command Dialog** on the right edge of the screen. On a phone, open it from its button in the top bar. See [Mobile and Accessibility](/command/features/mobile-and-accessibility.md).
2. Read the greeting. It is formal, for example "Good morning, Alex. What would you like to work on?".
3. Type your question and press **Enter**. Use **Shift+Enter** for a new line.
4. While it works, a short status such as **Working…** or **Checking the evidence…** shows. Press **Escape** or click **Stop generating** to stop.
5. Click a chip under the answer to take the next step.
To start over, click **Reset thread**, or type `/clear`.
### Ask about what is on screen
The chip above the message box shows the content the assistant will use as context: the icon and title of the item in your active tab.
* It **follows the active tab**. Switch tabs and the chip switches with you.
* Opening or creating an item attaches it.
* Home and full-page views such as Governance or the Glossary attach nothing.
* Click **×** (**Remove attached content**) to ask without context. This applies to the current tab only; switch away and back and it is attached again.
Then ask, for example, `explain this roadmap` or `what are we looking at?`.
### Confirm a write
Command Dialog writes to your instance only when you confirm.
1. Ask for a dashboard or a lifecycle.
2. Read the preview. It says what will be created and states that nothing is written yet.
3. Click **Yes, create it**, or type `yes`. Click **Cancel** to drop it.
A preview waits for Yes, create it
Content you ask for directly, such as a roadmap, a SWOT or an Advisory Report, opens straight away, the same as using the create menu. Command Dialog does not delete content in bulk.
### Plan a cost reduction
Ask, for example, `how can we reduce cost by 25% by end of this year?`. A **Cost reduction assessment** opens in the conversation and asks one question at a time. Anything you already said, such as the percentage, is filled in.
1. **Target**: the percentage reduction. Confirm with **Use this target**.
2. **Deadline**: pick a suggested date or give another one.
3. **Measures**: the cost measures maintained in your instance.
4. **Areas**: **Applications**, **Contracts**, **People** or **Infrastructure**.
5. **Scope**: which records to cover. **Assess every record**, or filter them.
6. **Basis**: **Recurring cost at the deadline** or **Savings realized during the period**.
7. **Baseline**: **Approved actual period**, **Approved budget** or **Approved forecast**.
8. **Constraints**: for example **Maintain service commitments** or **Exclude workforce changes**.
Your answers appear as chips at the top of the card. Click a chip's **×** to change that answer, or **Clear all** to start again.
{% hint style="info" %}
Today the flow captures and checks the scope of the assessment. It does not yet calculate savings or recommend changes. At the end it tells you which sources still need verifying before it can.
{% endhint %}
## Trust and evidence
Every recommendation says how much it can be trusted and why.
| On screen | Meaning |
| ------------------- | ----------------------------------------------------------------------------------------------------- |
| **Ready to decide** | The evidence is strong enough to act on. |
| **Needs approval** | The call should be made by a named person. |
| **Not ready** | The evidence is too thin. The report names the first gap to close. |
| Confidence **/100** | How certain the answer is. If the evidence holds it back, the report says so and what would raise it. |
Each piece of evidence carries a grade:
| Grade | What it means |
| --------------- | ---------------------------------- |
| **attested** | A person signed off on this value. |
| **measured** | Computed from governed data. |
| **declared** | Somebody typed it into a field. |
| **unsupported** | Nothing backs this read. |
How to read an answer:
1. Start with the verdict. It tells you whether you can act, who should decide, or what to fix first.
2. Check the confidence meter. A low score is not a "no"; it means the evidence needs work.
3. Look at the grades of the factors that matter most. Evidence a person signed off on counts for the most; a value nobody backs counts for nothing.
4. Every recommendation ends with a reminder that it is advice: nothing changes until a person acts.
Answers that contain a table open the table in a tab, and the conversation keeps a link to it.
## The Advisory Report
When you ask for a recommendation on one record, an **Advisory Report** opens in a tab. It re-reads your data every time you open it.
An Advisory Report opened from the Command Dialog
| Section | What it holds |
| -------------------------- | ---------------------------------------------------------------------------- |
| **Recommendation** | The verdict, and the option it was chosen over. |
| **Why: the factor ledger** | Each factor, where it came from, its grade and how much it moves the call. |
| **To raise confidence** | The evidence that would make the answer stronger, with links to the records. |
| **The record** | **Open form** and **Notify owner**. |
| **Board decision** | **Accept plan** records your decision. |
1. Read the verdict and the confidence.
2. Work through **To raise confidence**, or use **Notify owner** to ask the owner or steward to fix the data.
3. Click **Re-run assessment** once the data is fixed.
4. Click **Accept plan** to record the board decision. You are asked to confirm.
5. Click **Download PDF** to share it outside Command.
{% hint style="success" %}
An Advisory Report is advice. Accepting a plan records the decision; it does not change any lifecycle, investment or record. A named owner has to act on it.
{% endhint %}
## Privacy
| Question | Answer |
| ------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- |
| Where is my question processed? | In your browser. Command Dialog's language processing runs on your device. |
| Does anything go to a third-party AI? | No. Your questions and your data are not sent to any external AI service. |
| Where does the data come from? | Your ServiceNow instance. Command Dialog reads records with your own permissions and writes content and confirmed changes back to the same instance. |
| Does the tour change my data? | No. The guided demo builds its examples on your device and changes nothing in ServiceNow. |
## Good to know
{% hint style="warning" %}
The catalogue of governed business questions is switched off while it moves to a new library. If you ask `what can you answer?`, the list of governed questions shows 0, followed by the purpose-built actions that do work. The examples on this page are the ones that work today.
{% endhint %}
* If you ask for an analysis that has no method yet, Command Dialog says so instead of guessing. Cost reduction is the analysis available today.
* A shortlist says how many records qualify and how many are shown, for example "Eliminate 11 (top 10 shown)".
* Content Command Dialog creates appears in [My Space](/command/the-portal/my-space.md) under its own name, ready to use.
* An administrator can switch the assistant off for everyone in **Global Settings > General** (**Command SLM assistant**). Advisory Reports already created stay available.
## Related
* [Scoring](/command/features/scoring.md)
* [Data Governance](/command/features/data-governance.md)
* [Measures](/command/features/measures.md)
* [Content Types](/command/the-portal/content-types.md)
---
# 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.ins-pi.com/command/features/command-dialog.md?ask=&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.
