> For the complete documentation index, see [llms.txt](https://docs.eesel.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.eesel.ai/use-cases/helpdesk.md).

# Helpdesk

Your Helpdesk Agent works like a human agent: it drafts replies for review, triages and tags tickets, escalates the important ones, and answers from your own knowledge.

<figure><img src="/files/DA8sFmByzB0KkdDDR5d6" alt="eesel AI working as an agent inside a helpdesk, drafting a reply on a ticket"><figcaption></figcaption></figure>

## Quick start

{% stepper %}
{% step %}

### Talk to it to get started

Open the dashboard chat and tell it about your company: your name, your website URL, your help center. Or ask it to connect your helpdesk. It handles the rest.

<img src="/files/CUTPub5QOZMxaKNc3yED" alt="A chat where the user asks to set up a support agent and the agent walks through connecting Zendesk" width="563">
{% endstep %}

{% step %}

### Ask it a question

Test it with the questions your customers actually ask, and check which sources it uses to answer.

<img src="/files/ZiRK1QMrOXJsNcgDUx60" alt="The dashboard chat drafting an answer to a customer question, showing the help center sources it used and flagging a knowledge gap" width="563">
{% endstep %}

{% step %}

### Give it feedback

Tell it what was wrong, right there in the chat: too formal, missing a step, should have escalated. It updates its own instructions, so every correction sticks.

<img src="/files/wKnU2p0KpiMMzbfv7r3E" alt="A dashboard chat where the user asks for a more professional, shorter tone and the agent confirms it has saved three rules to its instructions" width="563">
{% endstep %}

{% step %}

### Put it to work

Ask it to start drafting replies, or tell it what you want it to handle. It creates an automation, which you can see and edit on the agent's **Automations** page.

<img src="/files/yWIY2tRtdcTqxVgAYa7d" alt="The Automations page showing two live automations next to the chat conversation that created them" width="563">
{% endstep %}
{% endstepper %}

***

## What it can do

* **Draft and send replies**, as internal notes for review or straight to the customer
* **Tag, categorize, and update tickets**, including fields and status
* **Escalate** to your team, by sentiment, low confidence, or your own rules
* **Answer in 80+ languages** without translating your help center
* **Match your tone and voice**, described in plain text

<figure><img src="/files/iUhiTs81rFwDq1KWZQ3R" alt="A Zendesk ticket with a drafted reply left by eesel AI as an internal note, including a link to view the draft in the eesel dashboard"><figcaption><p>The agent working inside your helpdesk. Here it's drafted a reply as an internal note on a Zendesk ticket, so an agent can review it before anything is sent.</p></figcaption></figure>

## Your team stays in control

Roll out gradually, the way you'd onboard a human teammate:

1. **Start with full oversight.** Every reply is a draft or waits for your approval.
2. **Let it go solo on the easy ones.** Once it gets the routine tickets right, let it answer those end to end.
3. **Hand over more as it earns it.** You decide when, and you can pull anything back at any time.

<figure><img src="/files/yStoy4RnPGeqAtKjZ6sS" alt="The dashboard showing an approval request, Allow eesel to use Leave public reply, with the drafted reply and Approve, Always Allow, and Deny buttons"><figcaption><p>Actions you haven't handed over yet wait for you. Approve once, always allow, or deny.</p></figcaption></figure>

## Correcting the agent

* **Give feedback in chat.** It updates its own instructions or adds the missing knowledge. See [Instructions and Memory](/instructions-and-memory/instructions-and-memory.md)
* **Edit the instructions yourself** on the Instructions page
* **Give it the docs you give your team.** Upload the procedures document you'd hand a new hire
* **Run a** [**Simulation**](/skills/skills.md)**.** It replays your past tickets and scores its answers against what your team actually sent

## AI copilot browser extension

The [eesel AI copilot](https://chromewebstore.google.com/detail/eesel-ai-chatgpt-sidebar/ejhkkbilnpifailgngpkgmiofhioacjd) is a sidebar you open on your helpdesk. Open a ticket and it has a draft reply ready. Paste it straight into the reply field, edit it first, or ask eesel to rework it.

<figure><img src="/files/nqI11CGqfvhM97bQwYdj" alt="A Zendesk ticket with the eesel copilot sidebar open, showing a drafted reply and a Paste into Zendesk button that puts it into the reply field"><figcaption><p>The copilot drafts a reply from the ticket you have open. <strong>Paste into Zendesk</strong> drops it into the reply field.</p></figcaption></figure>

## Skills

[Skills](/skills/skills.md) are extra workflows on top of the day-to-day ticket work. Run them on demand, on a schedule, or on a trigger, and just ask the agent in chat which skills to run or which ones to create. The ones most helpdesk teams start with:

* **Simulation**: replays past tickets and scores your agent's answers
* **Analyze ticket trends**: recurring topics, sentiment, and volume
* **Review agent setup**: audits your configuration and suggests improvements
* **Build a skill**: describe your own workflow in chat. See [Custom Skills](/skills/custom-skills.md)

<figure><img src="/files/FCd73xYDHHphAkcwmKSD" alt="The Helpdesk simulation skill page showing its description, what it does, and a chat panel running the skill"><figcaption><p>Each skill has its own page explaining what it does. Here, Helpdesk simulation replays past tickets in sandbox mode.</p></figcaption></figure>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.eesel.ai/use-cases/helpdesk.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.