> ## Documentation Index
> Fetch the complete documentation index at: https://docs.neoagent.io/llms.txt
> Use this file to discover all available pages before exploring further.
# Agents
> Neo Agents are AI-powered workers that can analyze tickets, communicate with users, and take action on your behalf
Neo Agents are the intelligent workers behind your workflows. Unlike simple automation rules, agents understand context, make decisions, and can handle complex multi-step tasks just like a human technician would.
Wondering whether to build an agent or a [workflow](/core/workflows) for your use case? See [Workflows vs Agents](/core/workflows-vs-agents) — start with workflows for triage, dispatch, resolution, escalation, and merge; reach for agents for everything else.
Discover the tools agents can use to accomplish tasks
Best practices and guidance agents load on-demand
## Building Your First Agent
Watch this 5-min walkthrough of building agents in Neo Agent:
## What Agents Can Do
Agents combine AI understanding with real-world actions. When a ticket comes in, an agent can:
* **Analyze** the problem using past tickets, documentation, and web knowledge
* **Communicate** with end users to gather information or provide updates
* **Take Action** in your PSA, RMM, or Microsoft 365 environment
* **Request Approval** from technicians before sensitive operations
Agents can also run **on a schedule without a ticket** — performing proactive tasks like M365 compliance audits, inactive account cleanup, and recurring admin operations.
Run agents on a recurring schedule for proactive tasks that don't start from a ticket
Agents your technicians and end users talk to directly — in the dashboard or via Teams
## How Agents Work
When a workflow triggers, the agent receives the ticket details, company information, and any custom instructions and [memory](/core/memory) you've configured. For [scheduled agents](/core/scheduled-agents), the agent runs from your custom instructions and enabled tools alone — no ticket needed.
The agent analyzes the situation, searches for relevant information, and determines the best course of action based on your instructions.
The agent selects and uses the appropriate tools to accomplish the task—whether that's searching documentation, updating a ticket, or communicating with a user.
After completing its work, the agent provides a detailed log of actions taken, along with any relevant outputs or recommendations.
## Agent Tools
Tools are the capabilities you enable for your agents. Each tool allows the agent to perform specific actions:
| Category | What It Does |
| ----------------------- | ------------------------------------------------------------------------------------------------------ |
| **PSA** | Read and write your PSA — tickets, notes, time entries, contacts, configurations |
| **RMM** | Read device and monitoring data, and run scripts on target devices to fix problems |
| **Microsoft 365** | Manage Entra ID, Active Directory, Exchange, and Intune — users, groups, licenses, mailboxes |
| **Communication** | Send messages to end users and internal teams — ticket notes, email, Teams, SMS |
| **Search** | Find documentation, similar tickets, configurations, and web resources |
| **Documentation** | Read and write IT Glue and Hudu resources — documents, configurations, assets, passwords |
| **Management** | Log time, generate passwords and secure links, trigger workflows, call external APIs and Neo's own API |
| **Built-in & Internal** | Tools the agent always has or gets automatically — search helpers, the sandbox, plumbing |
| **Approvals** | Request human approval before sensitive actions |
Tools are configured per-workflow. You choose which tools an agent can use and customize their settings to match your processes.
## Agent Skills
Skills provide specialized guidance that agents load on-demand. Unlike tools (which perform actions), skills teach the agent **how** to approach a type of task.
| Skill | What It Provides |
| -------------------------- | ------------------------------------------------------------------------------ |
| **Resolve Issue** | Structured diagnosis methodology, root cause analysis, and resolution planning |
| **End User Communication** | Message templates, tone guidelines, and safety rules for end user messaging |
Skills are always available and loaded automatically when relevant. Custom instructions take priority over skill guidance when there's a conflict.
You can also create **your own skills** for the repeatable procedures your agents run again and again — a weekly report, a monthly reconciliation — so every run comes out the same reliable way. See [custom skills](/agents/skills/custom-skills).
See all available skills, including how to build your own
## Credit Tiers
Tools are organized into credit tiers based on their complexity:
| Tier | Credits | Examples |
| ------------ | ------- | -------------------------------------------------------------------------------- |
| **Basic** | 1 | Trigger or Schedule Workflow, generate a password |
| **Standard** | 2 | Find PSA Contacts, documentation search, a read-only PSA or RMM integration |
| **Advanced** | 3 | PSA API with writes, Execute RMM Script, Microsoft 365 tools, external API calls |
Agent pricing is simple:
* Every Agent execution consumes credits
* The total credits for that execution equal the highest tier of any enabled Tool
* The agent can use enabled Tools unlimited times during that execution at no extra cost
For example, if you enable Find PSA Contacts (Standard, 2 credits) and the PSA API with ticket writes (Advanced, 3 credits), a single Agent execution costs 3 credits total.
The Agent can use both Tools any number of times during that execution with no additional credits.
## Best Practices
When test mode is on, the agent will not take any actions that have side effects (i.e updating tickets, creating time entries, etc.). Monitor agent decisions closely when first deployed to ensure quality.
For sensitive operations, start with Technician-in-the-Loop enabled. This gives you oversight while still benefiting from AI-powered analysis.
The better your instructions, the better the agent performs. Be specific about your processes, preferences, and edge cases. Iterate based on feedback to refine the agent's behavior. See [Writing effective agent instructions](/core/writing-agent-instructions) for the full guide.