The AI Agents feature lets you define reusable AI-powered agents and trigger them automatically on tickets through LiveAgent's automated rules engine. Instead of manually configuring an HTTP call inside every rule, you set up a named AI agent once — choosing which AI provider to use, which flow to invoke, and which actions the AI is permitted to take — and then reference that agent from as many rules as you like.
When a rule fires, LiveAgent dispatches the AI agent to your AI provider (currently FlowHunt), which processes the ticket and performs actions such as tagging it, resolving it, assigning it to an agent, or transferring it to another department — all without any human intervention.
Note: AI Agents requires an active FlowHunt AI provider integration. If you have not connected FlowHunt yet, complete that setup first before following the steps below.
How AI Agents Relates to Other AI Features
LiveAgent provides several AI-powered capabilities. AI Agents sits alongside them as a background automation layer:
| Feature | Who it serves | When it runs |
|---|---|---|
| AI Chatbot | Website visitors | During an active chat, before or instead of a human agent |
| AI Answer Assistant | Support agents | On demand, inside the ticket reply editor |
| AI Agents | Tickets (background) | Automatically, when an automated rule triggers |
Prerequisites
- FlowHunt account — You need a FlowHunt workspace with at least one AI flow configured to process LiveAgent tickets.
- FlowHunt AI provider integration — Go to Configuration > AI > Setup AI provider and connect your FlowHunt API key. See Integrating FlowHunt as an AI provider for step-by-step instructions.
- AI Budget — Create at least one budget under Configuration > AI > AI Budgets. Budgets define monthly tool call limits and must be selected when triggering AI agents from rules. See the AI Budgets & Credits section below for details.
Getting Started
Step 1 — Create an AI agent
An AI agent is the central configuration object. It tells LiveAgent which AI provider to call, which specific flow to invoke, and which actions the AI is allowed to perform on the ticket. You can create as many agents as you need — one per use case is a common pattern (e.g., one for auto-tagging, one for auto-resolving common FAQ tickets).
- Navigate to Configuration > AI > AI Agents and click Create AI agent.
- Enter a descriptive Name (e.g., Auto-classify inbound email). The name appears in rule actions and in the run log, so choose something that clearly identifies the agent's purpose.
- Under AI provider, select the FlowHunt integration you set up earlier.
- Under Flow, choose which FlowHunt flow should be invoked. The dropdown lists all flows available in the connected workspace.
- Under Allowed tools, select which actions the AI is permitted to take on the ticket. See the Allowed Tools reference below for a full list.
- Click Save.
Tip: Grant the AI only the tools it actually needs. For example, an agent whose sole purpose is to tag tickets does not need the Resolve ticket or Assign ticket tools. Keeping the tool list tight reduces the risk of unintended actions and helps conserve your credit budget.
Step 2 — Create MCP token and connect it in your flow
- In LiveAgent, edit the AI agent you created in Step 1. Under the MCP Tokens section, click Generate Token and copy the token.
- Go to your FlowHunt account and edit the flow you wish to use. Click your AI Agent node and under Tools click Add Tool.
- Search for and select the MCP Client tool.
- Click Edit Servers and enter
https://YOUR_ACCOUNT.ladesk.com/public/api/mcpas the MCP Server URL. Keep Transport asstreamable_http, select Bearer Token in Authorization, and paste your token from the previous step. - Save and adjust the prompt of your flow so it performs the actions you need.
Step 3 — Trigger the AI agent from an automated rule
- Navigate to Configuration > Automation > Rules (or Time Rules for time-based triggers) and click Create.
- Set a Trigger for the rule — for example, Ticket is created, Message is received, or Tag is added to ticket.
- Add any Conditions you need (e.g., only tickets in a specific department, or tickets with a particular subject keyword).
- In the Actions section, click Add action and select Run AI agent.
- In the action parameters:
- AI agent — Choose the agent you created in Step 1.
- Budget — Select which AI budget this run's tool calls should draw from. See the AI Budgets & Credits section for how to set up budgets.
- Click Save rule.
From this point forward, every time the rule fires, LiveAgent will dispatch the selected AI agent against the matched ticket. The run executes in the background — no further manual steps are needed.
MCP Server and Authorization Tokens
LiveAgent exposes a built-in MCP server (Model Context Protocol) that FlowHunt connects to when executing an AI agent flow. When the FlowHunt flow needs to read ticket data or perform an action, it calls LiveAgent's MCP server endpoint and LiveAgent executes the corresponding tool. This is the communication channel that makes the allowed-tools permission list enforceable — every call is authenticated and validated before it reaches the ticket.
The MCP server endpoint is: https://<your-liveagent-domain>/public/api/mcp
Tokens are valid for two years. If you use the same AI agent and FlowHunt flow for longer than that, rotate the token before it expires. All tokens for an AI agent are revoked automatically when the agent is deleted.
Allowed Tools Reference
Each AI agent includes a list of allowed tools — the specific actions it may invoke when processing a ticket. Tools not in the allowed list are unavailable to the AI for that agent, even if the underlying FlowHunt flow would otherwise request them. See the MCP Tools Reference for the complete list of all available tools and what each one does.
Monitoring Runs
Every time an AI agent is triggered for a ticket, LiveAgent creates a run record that tracks its full lifecycle. To review runs, navigate to AI Agent Runs.
Each run record shows:
- The AI agent that was executed
- The ticket that was processed
- Start time
- Number of tool calls made
- Current status and, if applicable, the failure reason
Run statuses
| Status | Meaning |
|---|---|
| Submitted | The run was created and sent to the AI provider. The FlowHunt flow is executing and may be making tool calls. |
| Waiting | The AI provider is temporarily throttled (rate-limited). LiveAgent will automatically resume the run once the throttle window expires — no action is needed on your part. |
| Completed | The AI made some tool calls within the past 10 minutes, and the run is therefore considered completed. |
| Failed | There were no tool calls made in the past 10 minutes and the run is considered failed. |
Possible failure reasons
| Reason | What it means | What to do |
|---|---|---|
| Timeout | The run was in the Waiting (throttled) state for more than 60 minutes and was automatically abandoned. | Check your FlowHunt plan limits. If throttling is frequent, consider reducing the number of rules that trigger AI agents simultaneously, or upgrading your FlowHunt plan. |
| LLM error | The AI language model returned an unexpected error during processing. | Review the FlowHunt flow configuration. If the error is intermittent, the next rule trigger will create a new run automatically. |
| Tool execution failed | The AI requested a tool call, but the action could not be completed (e.g., attempting to assign a ticket to an agent that no longer exists). | Review the FlowHunt flow logic and verify that referenced agents, departments, and tags still exist in LiveAgent. |
| Exceeded tool call limit | The run consumed its share of the selected budget's monthly allowance before completing. | Review the budget settings (see AI Budgets & Credits below), top up your credits, or simplify the FlowHunt flow to require fewer tool calls per ticket. |
| Ticket deleted | The ticket was deleted from LiveAgent while the AI was still processing it. | No action needed. This is expected behavior when tickets are removed during active processing. |
AI Budgets & Credits
Every tool call an AI agent makes draws from your account's pool of AI credits. You control spending through AI Budgets — named, monthly spending caps you manage under Configuration > AI > AI Budgets.
How it works:
- Credits are the underlying currency for AI agent tool calls. You can view your balance and top up under Configuration > AI > AI Budgets.
- Budgets set a monthly tool call cap. Create as many budgets as you need — for example, one per team or one per workflow type — and assign each rule action to the appropriate budget. Each budget's usage counter resets at the start of every calendar month.
- Budget assignment — When you set up a rule action in Step 3, you select both the AI agent and the budget it draws from. This lets you track and limit spend per workflow independently.
Important: If runs frequently fail with the "Exceeded tool call limit" reason, either increase the monthly limit of the selected budget, top up your credits, or simplify your FlowHunt flows to require fewer tool calls per ticket.
You can monitor your credit balance, per-budget usage, and estimated credit runway under Configuration > AI > AI Budgets.
Example Use Cases
Automatic ticket classification and tagging
Create an AI agent with the Get ticket messages and Add tags tools enabled. Build a FlowHunt flow that reads the first message, identifies the topic (billing, technical issue, feature request, etc.), and applies the corresponding tag. Attach this agent to a rule that triggers on Ticket is created for your general-support inbox. Every inbound ticket will be tagged within seconds of arrival, ready for agents to sort and prioritize.
Auto-resolve common FAQ tickets
Enable Get ticket messages, Add tags, and Resolve ticket for an AI agent. Configure the FlowHunt flow to check whether the ticket contains a standard question that can be handled without agent involvement, apply a tag such as auto-resolved, and then resolve the ticket. Use rule conditions to restrict this to specific departments or sender types so the AI only auto-resolves tickets where that is appropriate.
Intelligent ticket routing
Enable Get ticket messages, List departments, and Transfer ticket. Configure the flow to read the ticket content, determine the correct specialist team, and transfer the ticket automatically. This is especially useful when tickets arrive through a generic inbox and need to reach the right department before an agent picks them up.
SLA-aware escalation with Time Rules
Use a Time Rule instead of an instant rule. Set the trigger to fire when a ticket has been open for a defined period without a response. The AI agent can read the ticket context, assign it to a senior agent, and add an escalation tag — all without a supervisor having to manually monitor the queue.
Advantages Over Manual FlowHunt Rule Actions
LiveAgent previously supported triggering FlowHunt flows from rules using the generic HTTP request action (see Triggering FlowHunt AI agents via rules). The AI Agents feature is the recommended replacement for that approach and offers several important improvements:
| Capability | HTTP request action (legacy) | AI Agents |
|---|---|---|
| Setup complexity | Requires manually constructing the FlowHunt API URL, headers, and JSON body in every rule | Configure once in a named AI agent; reference by name in any rule |
| Reusability | Each rule requires its own complete HTTP action configuration | One agent can be reused across unlimited rules |
| Execution visibility | No built-in visibility into whether the flow ran, what it did, or whether it succeeded | Full run log with status, duration, tool call count, and failure reasons |
| Throttle handling | Rate-limit errors are not retried; the execution is silently lost | Throttled runs pause automatically and resume when the rate limit clears |
| Tool access control | The FlowHunt flow has no action restrictions imposed by LiveAgent | Each agent explicitly limits which actions the AI may take on a ticket |
| Budget protection | No centralized limits; runaway flows can cause unbounded tool usage | Monthly credit budgets protect against runaway runs |
| Authentication management | API keys are embedded directly in rule action fields as plain text | Tokens are managed centrally, scoped per agent, and revoked automatically when an agent is deleted |
Frequently Asked Questions
Can I use AI Agents alongside other actions in the same rule?
Yes. The Run AI agent action can be combined with other rule actions in the same rule. For example, you could send an auto-reply email and trigger an AI agent in the same rule, so the customer receives an instant acknowledgement while the AI processes the ticket in the background.
What happens if the same ticket matches two rules that both trigger an AI agent?
Each matching rule creates a separate, independent run. Both runs execute in parallel. If both try to write to the ticket (for example, both try to resolve it), the second write will apply after the first completes. To avoid conflicts, use rule conditions carefully to ensure that overlapping rules target different ticket states or departments.
Can I trigger an AI agent manually, outside of rules?
AI Agents are designed primarily for rule-based automation. Ad-hoc triggering from outside a rule is not currently supported in the LiveAgent panel. However, you can create a rule that runs an AI agent when a specific tag is added to a ticket — then simply tag the tickets you want the agent to process.
Does an AI agent run appear in the ticket's conversation history?
Yes. If the AI performs write actions (adding tags, resolving a ticket, assigning it, transferring it, etc.), those actions are recorded in the ticket's activity history. Agents can see exactly what the AI did and when.
Can I stop or cancel a submitted run?
Runs that are already Submitted cannot be cancelled mid-flight from the panel. Runs in the Waiting state will resume automatically once the provider's throttle window expires. If a run is already submitted and you cannot see any results for an unexpectedly long time, check the FlowHunt flow for loops or misconfigured steps that may be causing excessive tool call usage.
Is my ticket data sent to third-party AI providers?
The ticket content (messages and metadata) is transmitted to your configured AI provider — FlowHunt — for processing. FlowHunt is developed by Quality Unit, the same company behind LiveAgent, and adheres to the same data safety and privacy standards. If your FlowHunt flow uses an external language model (e.g., OpenAI GPT-4 or Anthropic Claude), your data will also be subject to that provider's terms. Review your FlowHunt flow configuration to confirm which underlying models are in use.