🤖 IT Agent

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 provider 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."

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

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)

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.

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.

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

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

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

6. Mentions

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

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.