> For the complete documentation index, see [llms.txt](https://docs.siit.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.siit.io/guides/ai/ai-it-agent.md).

# Get started with the IT Agent

Get an overview of the AI IT Agent: proactive issue resolution, automated actions through your connected tools, personalized support, playbooks and escalation to a human

{% hint style="info" %}
💡 Introducing **Siit's AI-Powered IT Support Agent** — the intelligent teammate designed to keep your IT operations running smoothly by delivering **autonomous, specialized, and personalized internal support**.

Whether it’s proactively resolving issues, automating playbooks, or escalating to a human at the right time, Siit’s agent is here to elevate your internal IT support experience.
{% endhint %}

#### What It Does?

* **Proactive Issue Resolution:** The agent monitors your environment to **identify and resolve problems before they impact your team.**
* **Automated Actions:** Define rules and instructions — the agent will **take action on your behalf**, fully integrated with your existing tools.
* **Contextual & Personalized Support:** The AI understands your company’s structure, tools, and processes to provide **instant and accurate support.**
* **Effortless Approvals:** Processes that once took days now take **minutes**. The agent handles approvals and keeps your team informed at every step.

### Glossary

***

* `Agent` Entity that will use LLMs to execute `actions` and provide an answer to the customer.
* `Action` Customer or Siit defined elements that will perform operations using Siit’s resources or fetch information.
* `Playbook` User written procedure defining how and when to use `actions`

#### Creating a Playbook

Define your IT processes using **natural language playbooks** and let your AI agent execute them, step-by-step.

### How to Build a Playbook

### 1. Condition

This is the trigger that will start the playbook.

> Example: "When an employee asks for new equipment."

<figure><img src="https://2274035325-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlWFhpq2ia6gdHet0opKx%2Fuploads%2Fgit-blob-fba2a2f26c4608afceaa19b61b34df357e1e1c89%2FCleanShot-2025-04-24-at-16.44.24-2x.png?alt=media" alt=""><figcaption></figcaption></figure>

### 2. Instructions

Describe the process you want the agent to follow using clear steps. You can include **actions** using `/` (e.g. `/create request`, `/send slack message`) which will open a popup to choose the specific action to trigger.

**Example Structure:**

* Step 1: Understand the Reason for Request
* Step 2: Determine Hardware Requirements
* Step 3: `/create request` for hardware
* Step 4: Notify the employee and their manager `/send slack message` with the Request ID

<figure><img src="https://2274035325-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlWFhpq2ia6gdHet0opKx%2Fuploads%2Fgit-blob-6d0c3ddc4818fbbd5b360dfe752dbd7e6299479d%2FCleanShot-2025-04-24-at-16.46.10-2x.png?alt=media" alt=""><figcaption></figcaption></figure>

### 3. Available Actions

AI agents can take many Siit or custom actions based on how they are configured.

Actions are used inside of Playbooks to allow the AI agent to take actions within Siit or your system or a third party.

Here’s a list of actions you can include in your playbooks:

* `/create request`
* `/submit request button`
* `/suggest article`
* `/send email`
* `/send slack message via Siit APP`
* `/send teams message via Siit APP`

**Okta**

`/okta reset multi-factor` *(Approval available)*

`/okta reset password` *(Approval available)*

`/Okta add to group` *(Approval available)*

`/okta add applications` *(Approval available)*

**Jumpcloud**

```
/Jumpcloud add to group
/Jumpcloud reset user password
/Jumpcloud reset user mfa
```

**Slack (Coming soon)**

```
/slack add user to channel managers
/slack add user to private channel
/slack add user to Public channel
/slack make channel private
/slack make channel Public
/Slack send message to channel
```

**Ticketing integration**

`/zendesk create ticket` *(Approval available)*

`/jira create issue` *(Approval available)*

`/webhook` *(Approval available)*

<figure><img src="https://2274035325-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlWFhpq2ia6gdHet0opKx%2Fuploads%2Fgit-blob-ae623aa1f9626ea60427b7325669134e51720cac%2FClipboard-20250424-144850-020.gif?alt=media" alt=""><figcaption></figcaption></figure>

### 4. Custom Actions

Maximize flexibility by defining custom actions within Playbooks:

1. **Descriptive Naming:** Assign clear, intuitive names and descriptions for each custom webhook action to facilitate understanding and execution by the AI agent.
2. **URL Specification:** Clearly define the external URL for requests to ensure precise data handling.
3. **HTTP Method Selection:** Use **`POST`** for transmitting data efficiently.
4. **Header Configuration:** Add necessary headers or opt for raw data input if using variables for customization.

<figure><img src="https://2274035325-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlWFhpq2ia6gdHet0opKx%2Fuploads%2Fgit-blob-7dccb371ed7f2ad16611ca63488fea8cf371012d%2FCleanShot-2025-08-08-at-15.40.02.gif?alt=media" alt=""><figcaption></figcaption></figure>

### 5. Approvals

For third-party apps: Specify how to handle approvals:

* Auto-run: Choose this for immediate execution without delays.
* Approval Required: Set conditions for necessary validations before execution.

<figure><img src="https://2274035325-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlWFhpq2ia6gdHet0opKx%2Fuploads%2Fgit-blob-96085019e8542283508869c590831c4a64e1d483%2FCleanShot-2025-04-24-at-16.41.23-2x.png?alt=media" alt=""><figcaption></figcaption></figure>

You have the ability to select the Approver that the agent will reach out to before executing the action. You will have the choice between

* Manager (Define dynamically based on the employee)
* Specific employees

Configure approval flows with rules like "First to approve" or "All users must approve."

<figure><img src="https://2274035325-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlWFhpq2ia6gdHet0opKx%2Fuploads%2Fgit-blob-827f9bb42b22aac7b07d9e86c04ad8d702a75b0d%2FCleanShot-2025-08-08-at-11.43.26-2x.png?alt=media" alt=""><figcaption></figcaption></figure>

### 6. Mentions

Use @mention smartly to direct notifications to relevant users, teams, or inboxes for updates, request escalations, or discussions. This helps in ensuring all necessary parties are informed and engaged.

<figure><img src="https://2274035325-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlWFhpq2ia6gdHet0opKx%2Fuploads%2Fgit-blob-91cc051561e03aeed94ab6a65c6e5071f76b914e%2FClipboard-20250424-145201-072.gif?alt=media" alt=""><figcaption></figcaption></figure>

### 7. Adding Articles

Enhance playbooks by incorporating relevant articles. These resources aid the AI in delivering deeper insights and more accurate responses to user queries.

<figure><img src="https://2274035325-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlWFhpq2ia6gdHet0opKx%2Fuploads%2Fgit-blob-e12d5f6b67a8501d5993e3e50af5d493e0774c04%2FClipboard-20250808-095048-076.gif?alt=media" alt=""><figcaption></figcaption></figure>


---

# 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.siit.io/guides/ai/ai-it-agent.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.