> For the complete documentation index, see [llms.txt](https://docs.harmony.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.harmony.io/ai-agents/software-management/application-health-check-discovered-applications.md).

# Application Health Check: Discovered Applications

The **Application Health Check: Discovered Applications** agent gives your team an automated, scheduled view of every application currently marked as Discovered in Harmony. Instead of running manual lookups to track down unreviewed or unmanaged applications, the agent surfaces all relevant details on a recurring basis so you can review, act, and stay on top of your discovered application inventory without extra effort.

### What This Agent Does

This autonomous agent runs on a schedule you define and automatically monitors all applications with a Discovered status in Harmony. For each discovered application, the agent collects and surfaces the following information:

* **Application details** - name, first discovered date, last seen date, owner, and all other available application metadata
* **Associated users** - full user information for every user linked to each discovered application
* **Associated instances** - all instance data tied to each discovered application

Because the agent runs autonomously, your team receives an up-to-date picture of your discovered application landscape without anyone needing to manually query or compile the data.

### Setting Up the Agent

To configure the Application Health Check: Discovered Applications agent, follow these steps:

1. Navigate to the **AI Agents** section in Harmony.
2. Locate and select **Application Health Check: Discovered Applications** from the available agent catalog.
3. Configure the schedule to define how frequently the agent should run - for example, daily, weekly, or at a custom interval that fits your review cadence.
4. Save your configuration to activate the agent.

Once activated, the agent begins running automatically according to your chosen schedule.

### Reviewing Agent Output

After each scheduled run, the agent surfaces its findings so your team can review the collected data. For each discovered application you will see:

* A summary of application metadata, including when it was first discovered and when it was last seen
* A list of users associated with the application, with full user details
* Instance information linked to the application

You can use this output to make informed decisions about each discovered application - such as approving it, flagging it for further review, or taking remediation steps based on your organization's policies.

### Use Cases

* **Reduce manual monitoring overhead** - Eliminate recurring manual lookups by letting the agent automatically surface discovered applications on a schedule.
* **Maintain application inventory hygiene** - Regularly review newly discovered or long-standing unmanaged applications before they become a compliance or security concern.
* **Accelerate review workflows** - Give your team consolidated, ready-to-act information for every discovered application, including user and instance context, in a single agent output.


---

# 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.harmony.io/ai-agents/software-management/application-health-check-discovered-applications.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.