Front
Set up an AI agent for the Front app. It drafts or sends replies in your shared inbox and tags and assigns conversations, trained on your help center.
eesel's AI agent for Front works inside your Front shared inbox: it drafts replies as internal comments or sends them, tags, assigns and archives conversations, and learns from your help center and past conversations.

What your agent sees
When a Front event starts a run, your agent already has:
The conversation: subject, status (unassigned, assigned or archived), tags, assignee, the customer's email address, custom fields and links.
Where it arrived: the inbox names and the address the customer wrote to.
The thread: the customer's messages, your team's replies and your teammates' internal comments, in time order. On a very long conversation only the newest page of messages is loaded.
For @eesel: the comment that called it and which teammate wrote it.
The customer: their Front contact (name, handles, lists and custom fields) and the account they belong to, if any.
Files: the list of files on the conversation. The images and PDFs the customer sent since your team last wrote (up to 5) come with the run, and the agent can open any other file when it needs it.
It does not see data from apps in Front's sidebar. Front is a shared inbox, so there is no open, pending or solved status, and closing means archiving.
Sources
Sources are what it learns from ahead of time:
Help Center
Your published help center articles. A full connection reads them from Front. Quick start crawls your public URL
Quick start or Full connection
Conversations
Your most recent Front conversations across your inboxes, at any status
Full connection
Every other integration on the agent is also a source, so a Front reply can draw on Confluence, Notion, your website, and your files at once. See Integrations.
What it can do
Triggers
Triggers are the Front events an automation can run on:
When a customer sends a message
A customer sends any inbound message
Full automation
front_conversation_replied
Only on the customer's first message
The first customer message eesel sees on a conversation
Triage and routing
front_conversation_created
Call @eesel in a comment
A teammate mentions @eesel in a comment
On-demand help
front_eesel_mentioned
Conversation closed
A conversation is archived
Post-resolution follow-up
front_conversation_archived
Actions
Actions are what it can do:
Respond
Send conversation reply
Sends a reply to the customer, with images or PDFs attached if needed
Draft conversation reply
Leaves a reply as a Front draft on the conversation, for a teammate to review, edit and send
Start a new conversation
Sends a new message from one of your Front channels, starting a conversation
Leave internal comment
Adds a comment only your team sees. Start here: the agent drafts, a human sends
Manage
Add tags
Adds one existing Front tag at a time
Remove tags
Takes one tag off the conversation and leaves the rest
Assign to teammate
Assigns the conversation to a specific person
Close conversation
Archives the conversation
Update conversation
Moves the conversation into another inbox, which is how Front hands it to a team, opens an archived conversation again, or updates other fields that have no action of their own
Look up
Read conversation / List conversations / Search conversations
Reads a conversation's full message thread and its inboxes, lists the most recent conversations, and searches all of them by words, customer, inbox, tag, assignee or status
Look up a contact / Get attachment
Reads a customer's Front contact record, and opens a file attached to a conversation
Search message templates
Lists or searches your saved Front message templates, with their text
List tags / List teammates / List inboxes / List channels
Lists your tags, your teammates with the ids assignment needs, your inboxes with the team that owns each, and the addresses Front sends from
You stay in control the whole way. Adjust your AI agent's access to knowledge and its action permissions to your liking. See Actions and Approvals.
Set up eesel in Front
Choose Quick start or Full connection
Quick start. Give your public help center URL (for example
https://help.yourcompany.com), click Start Crawling, and it reads your articles. No sign-in, but no conversations, triggers or actions.Full connection. Approve eesel in Front, and everything unlocks: your Front help center and past conversations as knowledge, triggers, and actions.
Start with either. You can move to a full connection later and keep everything.
Quick start asks for the URL and nothing else.

Approve it in Front
For a full connection your agent hands you a link.

Front asks you to authorize eesel and to pick which workspaces to grant. It then lists every resource the token can read and write. Review it and click Authorize.

This approval is the one step a person has to do in the browser. If an AI agent is doing the setup for you, it hands you the link and waits.
Check what it can read
Back in the dashboard, Integrations > Front shows the connection and its sources, each with its own toggle. Each source shows a document count once its sync is done. From a terminal, eesel status lists the integration as connected with its source counts.

Create your first automation
Connecting alone does not start your agent. It needs an automation first. Tell it what to handle and it creates an automation. An automation is a Front trigger plus instructions. In the instructions you describe which conversations it should handle and what to do with them. Skipped conversations are recorded on the agent's Activity page, so you can see what was passed over and why.

It shows up on your Automations page, switched on and ready. From a terminal, eesel automations lists it as on.

Open the automation to see or change what it does. The trigger event is fixed when the automation is created. So a new automation is required for each different trigger event.

Check automation work in Front
Open Front and look at the next conversation that comes in to see what the automation did there. In this example it left a drafted reply as an internal comment, posted by eesel, for a teammate to review and send.

Things to know
Tags must already exist. The agent never creates a tag in Front. It adds or removes one tag at a time.
A team gets a conversation through its inbox. Front has no team assignee, so to send a conversation to a team the agent moves it into one of that team's inboxes. That move uses Update conversation, so leave that action on if you want the agent to route to teams.
Search is live. The agent searches your Front conversations directly, so it can find an older one by customer, tag or words, not only the recent ones it has synced.
Past conversations are not only resolved ones. The sync pulls recent conversations at any status, so treat them as context rather than approved answers.
"First message" means the first one eesel sees. If you switch the trigger on while a conversation is already open, the customer's next message there counts as its first.
@eesel only works in the newest comment. The agent reads the latest comment on the conversation, and ignores it unless it mentions @eesel.
Only a sent reply carries files. Send conversation reply can attach images and PDFs, either sent in the conversation or saved in the agent's Files folder (up to 25 MB in total). Drafts, new conversations and internal comments are text only.
A failed read is not announced. If Front does not return the messages or comments, the run goes ahead with what it has and is not told the thread is missing.
One trigger per automation. The trigger event is fixed when the automation is created, so each trigger needs its own automation.
Troubleshooting
FAQ
Related pages
Helpdesk for the job your teammate takes on in a ticket queue
Automations and Schedules for triggers, instructions and schedules
Actions and Approvals for choosing what your agent may do
Integrations overview for how sources, triggers and actions fit together
Last updated

