AI Features Overview
What TicketCord's AI features do, where to turn them on, which plan each one needs, and how tokens work
TicketCord's AI features answer questions from your own documentation, sort and prioritize tickets, translate conversations, and warn your team when a customer is upset. Each feature is switched on separately per server, so you can start with one and add more when you are ready. This page is for the server admin who sets them up.
AI features require a Pro or Enterprise plan on the bot owner's account. Sorting, Translation for tickets, and Mood history are Enterprise only. The 14-day signup trial runs as Enterprise with a one-time allowance of 1,000,000 tokens. View pricing
Available AI features
Answers questions in tickets from your documentation, Discord channels, uploaded files, and GitHub, and learns new answers from closed tickets.
Moves new tickets to the right category based on routing rules you write in plain language.
Sets Low, Medium, High, or Urgent on new tickets and adds a priority emoji to the channel name.
Posts a card in your logs channel when a new ticket repeats or relates to a recent one.
Translates messages between the customer's language and your staff language.
Pings a role when a customer sounds angry, frustrated, upset, or confused.
Manage tickets and the knowledge base from an AI coding tool over MCP.
The name your AI uses when it answers in Discord, and what it can and cannot do.
The AI assistant → Atlas page also holds three smaller features that work the same way (a switch on the card, its settings under it): Ticket summary (a short note for staff on each new ticket: what the customer needs, how they feel, and how urgent it is), Ask for details (replies when a customer only says hello and asks what they need), and AI Help for staff (an AI Help button on the ticket welcome message that drafts a reply for staff to review). All three are Pro and higher.
Where the settings live
Go to AI assistant → Atlas Go to AI assistant → Knowledge baseOpen the server
Go to your server, or click its tile on the dashboard home.
Open AI assistant
Go to AI assistant, under Settings in the sidebar. A switch at the top of the page shows one of two blocks at a time: Atlas (the AI features) and Knowledge base.
Choose a feature on Atlas
Atlas puts all its feature cards on one page: Tone alerts, Mood history, Automatic priority, Ticket summary, Duplicate tickets, Ask for details, AI Help for staff, Sorting, and Translation. On Pro, Mood history, Sorting, and Translation show locked cards with an Enterprise badge. Search for a feature by name with Search settings to choose a server and jump straight to its card. The Knowledge base block has its own tabs: Sources, Answering, Auto support, Learning, Staff Q&A, and Stats, under a Use the knowledge base switch that turns it on or off.
Turn on the master switch
Switch on the Atlas card at the top of the page. Until you do, the feature cards are replaced by Atlas is off and those automatic features do not run. Enabling Atlas activates your saved feature choices; switch each feature on or off on its card.
Save
Your changes collect in a bar at the bottom of the page. Click Save changes to apply them or Undo changes to drop them. Nothing is applied until you save. You can keep editing while a save is in progress; later changes stay unsaved in the bar until you save again.
Server-wide settings
These settings, on the AI assistant → Atlas page, apply to every AI feature on the server. The Atlas master switch sits at the top; shared reading, member usage, and exclusion controls sit below the feature cards.
| Setting | Options | Default | What it does |
|---|---|---|---|
| Atlas (the switch at the top of the page) | On, Off | Off | Master switch for automatic features on this server. Staff-requested commands such as /summary and /ai-help remain available with their own plan and permission checks. |
| How much Atlas reads | Full, Standard (recommended), Minimal | Standard | Full sends whole messages, formatting included: the most accurate, and the most tokens. Standard sends the text with enough context around it. Minimal sends only the key text and uses the fewest tokens. |
| Usage limit per member | On, Off; Tokens per member (1,000 to 100,000,000); Resets every Day, Week, Month, or Year | Off; 100,000 tokens a month | Caps how many AI tokens each member can use in their tickets. Staff are never limited. When a member reaches the limit they are told, and AI features stay off for them until the next period. The bot owner can clear usage with Reset usage: Reset one member… or Reset everyone…. |
| Members without Atlas | Up to 500 members | Empty | Atlas stays out of tickets these members open; staff still see and answer them. Manage opens the list, where you add members by name or Discord user ID. |
What happens
Every feature follows the same pattern:
- Something happens in a ticket: it is created, or the customer sends a message.
- The bot waits for the feature's delay so it can read follow-up messages together. Most features wait 30 seconds by default; the knowledge base waits 10 seconds. In ModMail the knowledge base starts right away instead, and each answer covers everything the member wrote since the last answer or staff reply, so a follow-up such as "hi" never replaces the question with a greeting.
- The AI reads the conversation and makes a decision with a confidence score.
- If the confidence is above the feature's threshold, the action runs: an answer is posted, the ticket is moved, the channel is renamed, or a card is posted to your logs channel.
- Where a feature has feedback (knowledge base votes, learning from closed tickets), your team's input improves later answers.
Several features report to the logs channel (set in Post logs in under General → Logs channel). If no logs channel is configured, priority cards, duplicate cards, tone alerts, and learning notifications are not posted, but the feature itself still runs.
AI tokens
Tokens are the budget every AI feature draws from. Each plan includes a monthly allowance:
| Plan | Tokens per month |
|---|---|
| Free | 0 (no AI access) |
| Basic | 0 (no AI access) |
| Pro | 10,000,000 |
| Enterprise | 30,000,000 |
- Usage resets with your billing period. Open AI usage (in the sidebar's More tools group on the dashboard home, or in the account menu) to see tokens used, when they refill, the daily average, and how many you are expected to use by the reset.
- Need more? Token packages of 10M, 20M, or 50M tokens are available under Extra tokens on the AI usage page, and Enterprise triples the monthly allowance.
- A priority check uses about 700 tokens (the estimate shown under What each priority means on the Automatic priority card). Other features depend on message length and How much Atlas reads, so the AI usage page is the reliable place to see real consumption.
- On the signup trial, AI features pause when the 1,000,000-token trial allowance is used up. Upgrading restores the full monthly allowance.
Limits and gotchas
The plan check uses the bot owner's plan, not the plan of the dashboard staff member changing settings. If the owner downgrades, AI features stop even though the switches still look on.
- Every AI feature respects Members without Atlas on the AI assistant → Atlas page: members on it never receive AI answers in tickets they create. The list holds up to 500 members.
- Only answer outside business hours on the AI assistant → Knowledge base → Answering tab needs business hours, which are an Enterprise feature.
Troubleshooting
| Symptom | Cause | Fix |
|---|---|---|
| The feature cards are hidden and the page says Atlas is off | The Atlas master switch is off | Switch on the Atlas card at the top and save |
| A feature shows a Pro+ or Enterprise badge and its switch is greyed out | The bot owner's plan is below the feature's requirement | Upgrade the owner's plan (the badge links to Plan & billing); dashboard staff cannot unlock it |
| Features are on but nothing happens | The owner's monthly tokens are used up, or the trial allowance is exhausted | Check AI usage; wait for the reset or add a token package |
| A ticket creator gets no AI answers but others do | They reached the Usage limit per member or are on Members without Atlas | Reset them with AI assistant → Atlas → Usage limit per member → Reset usage, or remove them from the list |
| Cards never appear in the logs channel | No logs channel is configured, or the bot cannot post there | Choose a logs channel under General → Logs channel (Post logs in) and give the bot View Channel and Send Messages in it |
| The bot replies with TC014 | The action needs a higher plan | See TC014 |
Common questions
Do I need to turn on every AI feature? No. Each feature has its own switch. A common start is the knowledge base alone, then Automatic priority once you trust the answers.
Can dashboard staff change AI settings? Yes, if they have dashboard access, except for owner-only actions: managing text file and GitHub repository sources, status page integrations, and resetting user token usage.
Do AI features work on the Free or Basic plan? No. Both plans have no AI access and 0 tokens. Pro and Enterprise include AI. The signup trial gives Enterprise access for 14 days.
Which features are Enterprise only? Sorting, Translation for tickets, and Mood history (the mood journey on the ticket page). ModMail translation is available from Pro.
Where do I see how many tokens I have left? On the AI usage page, in the sidebar's More tools group on the dashboard home or in the account menu. It shows the tokens from your plan, tokens used, when they refill, and how many you are expected to use by the reset.
What happens when tokens run out? AI features pause until the next billing period or until you add a token package. Tickets keep working normally without AI.
Does the AI read every message? Only messages in tickets on servers where a feature is switched on, and only as much as How much Atlas reads allows. Staff messages are used to decide when the AI should stay quiet and, for learning, which answers were correct.
Join our Discord server for support
Was this page helpful?
Last updated on