Front

Invite your AI teammate into Front so it drafts or sends replies in the shared inbox, assigns and archives conversations, and learns from your help center and past conversations.

Front is a shared inbox, not a ticketing tool. A conversation is unassigned, assigned, or archived. There is no open, pending or solved status. Your agent works the same way your team does. It reads your help center and your past conversations, so it knows how you answer before it picks anything up. Then it works your inboxes the way you tell it to: writing replies for a human to check, answering the routine ones itself, tagging and routing the rest.

You stay in control the whole way. Nothing runs until you create an automation. For each action you then choose: run on its own, ask you first, or stay off.

In this example the conversation is assigned to eesel AI, the way you would assign one to a teammate.

A Front conversation about adding a seat mid-cycle, assigned to eesel AI, with the internal comment it left.

Quick start

1

Ask your agent to connect Front

Open the chat in your dashboard and ask it to connect Front. It lays out both ways to connect. Prefer to click? Integrations in the left sidebar has the same options.

The agent offers two ways to connect Front.

2

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: 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.

The Quick start form, with a help center URL entered.

A full connection does not ask for your help center URL. It syncs conversations and account data only. So your help center stays empty until you add the URL yourself. Open Integrations > Front, find the Help Center source, and paste your help center URL into it, or connect with Quick start as well.

3

Approve it in Front

For a full connection your agent hands you a link.

The agent posts the approval link in the chat.

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.

The Front approval screen, with the workspace picker and the permissions list.

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.

4

Confirm the connection

Once you approve, your agent notices the connection on its own. It confirms in chat and starts reading your conversations and inbox setup.

The chat confirms Front is connected.

5

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.

Each source has its own toggle and its own document count.

6

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.

Ask in chat for the automation you want, and the agent builds it.

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

The new automation on your Automations page, switched 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.

The automation editor, where you change the instructions it follows.

7

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.

The drafted reply waiting as an internal comment on the conversation.

From Claude Code, Cursor or a terminal. The same setup works as commands: eesel login, then eesel integrations connect front (a person approves it in the browser; if the receipt has no link, ask eesel chat for one), eesel integrations download start to copy your sources in, and eesel automations to see and switch on the automations. Trigger keys for this page are in the Triggers table below. Full command reference: The eesel CLI. Step-by-step: Set up from Claude Code or the terminal. From an MCP client: Claude Code and MCP clients.

Sources, triggers and actions

Sources

Sources are what it learns from:

Source	Description	Requires
Help Center	Your public help center articles, read by our web crawler	Quick start, or a URL added after a Full connection
Conversations	Your past Front conversations across your inboxes	Full connection

The conversation sync isn't limited to resolved conversations: it pulls your most recent conversations at any status, so treat them as context for tone and history rather than a library of approved answers. 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.

Triggers

Triggers are the Front events an automation can run on:

Trigger	Fires when	Best for	Key
When a customer sends a message	A customer sends any inbound message	Full automation	front_conversation_replied
Only on the customer's first message	A new conversation is opened by a customer	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, each set to run on its own, ask you first, or stay off:

	Action	What it does
Respond	Send conversation reply	Sends a reply to the customer
	Leave internal comment	Adds a comment only your team sees. Start here: the agent drafts, a human sends
Manage	Add tags	Adds tags to the conversation. The tag must already exist in Front
	Assign to teammate	Assigns the conversation to a specific person, not a team
	Update conversation	Updates conversation fields
	Close conversation	Archives the conversation. Front has no open, pending or solved statuses
Look up	Read conversation / List conversations	Reads a conversation's full message thread, and lists the most recent conversations
	List tags / List teammates	Lists your tags, and your teammates with the ids assignment needs

Troubleshooting

Help center shows 0 documents after a full connection?

Add your help center URL under Integrations > Front and re-sync. The full connection never asks for it. If it still shows 0, check the URL is publicly accessible and the articles are published rather than drafts.

Agent not picking up conversations?

Check the automation is enabled on the agent's Automations page, its instructions cover the conversations you expect, the Front connection is still authorized, and at least one action is enabled.

Tagging or assignment failing?

Tags have to exist in Front already; the agent never creates new ones, so create the tag there first. Assignment goes to one specific teammate, not a team or a group; routing to a group is still something a human does in Front.

Full connection failing?

Make sure you have the rights in Front to authorize an app, and that you granted access to the workspaces you actually want the agent working in. Then disconnect and reconnect.

FAQ

Does connecting Front start replying to customers automatically?

No. Connecting only gives your agent access to your sources. It won't act until you enable a trigger and an action, so you can test with a human in the loop first.

How do I keep a human in the loop?

Two ways, and you can use both. Turn on Leave internal comment instead of Send conversation reply, so the agent writes its answer as a comment your team reads, edits and sends. Or set an action to ask you first, so the agent shows you exactly what it wants to send and waits. Start with internal comments, then move to sending replies once you're happy. When an action is set to ask you first, the prepared reply shows up in the dashboard with three buttons: Approve runs it once, Always allow stops asking for that action, and Deny discards it.

Can I limit which conversations the agent handles?

Yes. In the automation's instructions, describe the conversations you want in plain language, by tag, inbox or topic, and what to do with them. The agent only runs on the ones that match. Skipped conversations are recorded on the agent's Activity page, so you can see what it passed over and why.

Can the agent train on my past Front conversations?

Yes, with a full connection. See the Conversations source above for what the sync pulls in.

How is this billed?

Pay-as-you-go: a conversation your agent handles is one task, however many replies happen on it, and chats you run yourself from the eesel dashboard are free. See Pricing for rates, the annual commitment, and Enterprise.

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 setting each action to run on its own, ask you first, or stay off

• Integrations overview for how sources, triggers and actions fit together

• Set up from Claude Code or the terminal