Skip to main content
Tools define what actions Neo Agents can perform. When you configure a workflow, you select which tools are available and customize their settings to match your processes.
Some tools turn on automatically once you configure an integration’s permissions on the agent’s Tools & Settings tab — the PSA, RMM, Microsoft 365, and documentation API tools (IT Glue, Hudu, Lexful, Confluence, SharePoint) all work this way. You pick which permission groups the agent can use; the matching tool appears without a separate toggle.

​
Tool groups

The rail on the agent’s Tools & Settings tab groups the tools the same way the Integrations page does:
  1. Integration categories, under their sections. Service Desk, Security, Infrastructure, Communication and Business each open to show their categories, and Other is one row. Every category is listed, so you can see what Neo connects to. A section starts open when the agent has something switched on in it; click its heading to open or close it. A vendor’s tools sit in its main category. Neo’s own tools for a system sit with that system: the Microsoft 365, Exchange and Active Directory tools under Identity & Workspace, the license seat tools under Cloud Marketplace, and the TimeZest link tool under Scheduling & Field Service.
  2. Neo capabilities. These groups belong to no one system: Search, Messaging (email, SMS, Teams and Slack messages, client-facing notes), Approvals and the others. The read-only Built-in Capabilities list comes last.
The number beside a group or section is how many of its tools and permissions are switched on for this agent. A category shows an integration only when it is connected. Microsoft 365, Active Directory and Exchange always show. If you disconnect an integration that the agent still has permissions on, it stays with a Not connected badge, so you can set those permissions to None. A category with nothing connected is dimmed. Open it and it names the vendors you can connect there, with a button to browse them. A category that has connected integrations ends with the vendors you could still add, for example “Also in RMM: connect Datto RMM, N-sight, N-central and 6 more in Integrations”. If you search the tab for a vendor that is not connected, the tab tells you so, for example “Sophos is not connected. Connect it in Integrations”. Each of these links opens the Integrations directory in a window over the agent, so you never leave the agent or lose an unsaved change. A vendor that connects with credentials is set up in that window; the others, such as a PSA or a vendor that signs in through its own site, open their setup on the Integrations page in a new tab. Close the window and the tab shows what you connected. An end-user chat agent has a fixed set of tools, so its tab does not change with your connections.

Tool credit costs

What each tool costs, and why a scheduled or chat agent is billed per call — not once per run

PSA

Read and write your PSA — tickets, notes, time entries, contacts, configurations, and more

RMM

Read device and monitoring data, and run scripts on target devices to fix problems

Documentation

Read and write documentation in IT Glue, Hudu, Lexful, Confluence, and SharePoint

Identity & Workspace

Manage Entra ID, Active Directory, Exchange, and Intune — users, groups, licenses, mailboxes

Vendor integrations

One tool per connected vendor, in the vendor’s category group: security, networking, backup, phone, sales and more

Search

Find documentation, similar tickets, configurations, and web resources

Messaging

Send messages to end users and internal teams — client-facing notes, email, Teams, Slack, SMS

Approvals

Request human approval before sensitive actions

Built-in & Internal

Tools the agent always has or gets automatically — search helpers, the sandbox, passwords and secure links

Other

Trigger or schedule another workflow, and call external APIs and Neo’s own API

​
Credit Tiers

Each tool has a tier. What you pay depends on how the agent runs, not only on which tools are enabled.
For the API-backed integration tools (PSA, RMM, Microsoft 365, the documentation platforms and the vendor APIs), a triggered agent’s tier reflects the access you grant — Standard when every enabled permission group is Read Only, Advanced when any group allows writes. On a scheduled or chat agent, each call prices by what it did: see Tool credit costs.
Tools Neo adds for you never set a triggered agent’s per-run price. Searches, the sandbox, and similar always-on tools are listed under Built-in Capabilities with no price tag. On a scheduled or chat agent they still bill when called — Find Documentation is 2 credits per search, Sandbox Bash is 2 per call. Skills in that same list are free to load; the tools they use are not. The full table is on Tool credit costs.

​
Tool Dependencies

Some tools automatically enable other tools they depend on. For example:
  • Execute RMM Script automatically enables the device-lookup and script-search capabilities it needs
  • Update and create operations automatically enable the field-options lookups they need
Dependency tools are shown in each tool’s documentation. They’re automatically enabled when you select the parent tool.

​
Technician-in-the-Loop

Many tools support Technician-in-the-Loop approval, which requires human approval before the agent takes action. When enabled:
  1. The agent prepares the action and explains what it wants to do
  2. A Teams message is sent to configured technicians
  3. A technician approves or rejects the action
  4. The agent proceeds based on the decision
Start with approval enabled for sensitive operations. As you gain confidence in the agent’s decisions, you can disable approval for routine tasks.