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

# AI in your helpdesk

See how recording requests, report intelligence, knowledge sources, and AI Resolution fit your support workflow.

Your helpdesk remains where your team manages the conversation and sends replies. Screendesk adds visual evidence and AI analysis to help the agent understand the issue before deciding on the next step.

The available capabilities differ by integration.

## Compare the workflows

| Helpdesk               | Collect customer recordings                                           | Import resolved conversations into Data Sources | Automatic AI Resolution private notes                  |
| ---------------------- | --------------------------------------------------------------------- | ----------------------------------------------- | ------------------------------------------------------ |
| **Zendesk**            | Recording requests and supported form/chat flows                      | Yes                                             | Yes, for eligible recording-linked tickets after setup |
| **Intercom**           | Messenger, conversation sidebar, Workflows, and Fin-assisted requests | Yes                                             | Not part of the current AI Resolution workflow         |
| **Freshdesk**          | Screendesk recording integration and portal workflows                 | Yes                                             | Not part of the current AI Resolution workflow         |
| **Freshchat**          | Screendesk recording integration                                      | Yes                                             | Not part of the current AI Resolution workflow         |
| **Other integrations** | Use the recording features documented for that integration            | Limited to the providers listed above           | Not part of the current AI Resolution workflow         |

Report intelligence is a Screendesk capability: when available and enabled, your team can review the analysis on the eligible recording or report. Connecting a helpdesk does not by itself enable every AI feature.

## A support agent's workflow

### 1. Ask the customer to show the issue

Use the helpdesk's Screendesk integration to request a recording in the context of the ticket or conversation. Ask the customer to show the steps leading to the problem and explain what they expected.

Captured browser information, console logs, and network activity depend on the recording method and configuration.

### 2. Review what happened

Open the submitted recording in Screendesk. Use its summary, reproduction steps, and transcript when available to find the relevant moment quickly.

This step is useful even when AI Resolution is not available for your helpdesk.

### 3. Use knowledge to investigate

Maintain current documentation and procedures in [Data Sources](/debug-with-ai/data-sources.md). Resolved conversations can provide similar cases, but they remain separate from trusted product documentation.

For an eligible Zendesk ticket, [AI Resolution](/debug-with-ai/ai-resolution.md) can perform this investigation automatically and post a private note.

### 4. Decide how to respond

Review the evidence and any suggested reply. Edit the response for the customer's situation, then send it from your helpdesk.

If the issue needs engineering, use [Send to apps](/request-screen-recording/send-to-apps.md) to prepare an issue in Linear, GitHub, or Jira, or investigate the report with [MCP](/debug-with-ai/mcp.md) or the [CLI](/debug-with-ai/cli.md).

## Zendesk: an investigation inside the ticket

After [AI Resolution setup](/debug-with-ai/ai-resolution.md), an eligible customer recording triggers an investigation using the current ticket, recording analysis, published guidance, and trusted knowledge.

Agents receive a private **AI Resolution** note with supporting context and, when available, a recommended reply. The customer does not receive the private note.

Screendesk's automatic public-reply setting must be off for AI Resolution. You can still use a Zendesk trigger or macro to ask the customer for a recording.

A recording receipt, report-intelligence note, and AI Resolution note serve different purposes: receiving media, summarizing evidence, and investigating a possible next step.

Start with [Zendesk installation](/helpdesk-integrations/zendesk/install-and-set-up.md) and [AI Resolution](/debug-with-ai/ai-resolution.md).

## Intercom and Fin: collect evidence before handoff

Fin can be configured to suggest a Screendesk recording when a customer reports a bug or unexpected behavior. The submission provides context for the agent who handles the conversation.

This is a recording-request and handoff workflow. It does not mean that Fin automatically runs Screendesk AI Resolution or receives access to your private Screendesk knowledge.

You can also import closed Intercom conversations into Data Sources as internal case memory.

See [Fin setup](/helpdesk-integrations/intercom/fin.md) and [Intercom installation](/helpdesk-integrations/intercom/install-and-set-up.md).

## Freshdesk and Freshchat: capture and reuse support context

Use the recording integration to collect evidence and review available analysis in Screendesk. Import resolved tickets or conversations when you want that history available as internal case memory.

Importing that history does not enable automatic investigation notes in Freshdesk or Freshchat.

See [Freshdesk](/helpdesk-integrations/freshdesk.md) and [Freshchat](/helpdesk-integrations/freshchat.md).

## Put each instruction in the right place

* **Helpdesk or bot configuration:** when to ask for a recording and how to route the conversation.
* **AI & Intelligence settings:** whether Screendesk processes new content and analyzes reports.
* **Data Sources:** product facts, procedures, and historical cases.
* **AI Resolution guidance:** evidence requirements, response style, privacy rules, and escalation criteria.

See [AI overview](/debug-with-ai/overview.md) for the full setup path.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.screendesk.io/debug-with-ai/ai-in-your-helpdesk.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.