> ## Documentation Index
> Fetch the complete documentation index at: https://docs.parahelp.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Improve

> Your product ships daily, and your agent keeps up.

Your product ships daily, and your agent keeps up. Automations watch GitHub, Linear, Slack, and your support queue (see [Automations](/platform/automations)) - when your product changes or a human handles a ticket, the Internal Agent reports the impact and proposes the update in a [task](/platform/tasks). Each proposal starts the next build, and the loop keeps turning.

## How it works

<Steps>
  <Step title="Automations watch your tools">
    GitHub, Linear, Slack, and your support queue. See [Automations](/platform/automations).
  </Step>

  <Step title="The Internal Agent proposes updates">
    It creates todos for the high-leverage improvements it identifies in automations and one-off tasks: knowledge gaps, tool ideas, and flow improvements. Each todo comes with the relevant context and attributes, assigned to the right user or team.
  </Step>

  <Step title="You start the todo">
    One click opens the task, and the next build begins. See [Build](/internal-agent/build).
  </Step>
</Steps>

Todos appear on the [Tasks page](/platform/tasks) and in your [Inbox](/platform/inbox).

## Reporting

Track your Customer Agent's performance in Parahelp or in your ticketing system's own reports.

<Accordion title="How tickets are counted" icon="sitemap">
  Every ticket falls into one branch:

  * **AI engaged:** Your Customer Agent replied to the ticket or took action on it.
    * **AI resolved:** The agent closed the ticket, and it stayed closed for at least 3 days. Split into general, spam, and merged tickets.
    * **Engaged, not resolved:** The agent engaged, then handed the ticket to a human for final resolution (previously called "assisted").
  * **AI not engaged:** Your Customer Agent never worked the ticket.
    * **Not routed to AI:** The ticket was never assigned to the agent, for example because your routing workflow excluded it.
    * **AI ignored:** The ticket was assigned to the agent, but it stayed out, for example because the ticket type is out of scope in its instructions.
</Accordion>

### Ask the Internal Agent

The Internal Agent covers both the numbers and the why - including the impact of every release on your resolution rate.

* **Quantitative reports.** *"Show me a graph of resolved tickets over the past month"* gets you an interactive chart, sortable by category. It can analyze any slice of your ticket data.
* **Qualitative reports.** Patterns, trends, and representative quotes across your tickets. Common ones: performance reports, bug-pattern reports, and improvement reports.

Run either on demand in a task, or daily and weekly as an automation (see [Automations](/platform/automations)).

<Frame>
  <img src="https://mintcdn.com/parahelp/4tA31uJTnpSG6ZY4/snippets/reporting.png?fit=max&auto=format&n=4tA31uJTnpSG6ZY4&q=85&s=085786cd23d97a07f878350b7ab826b1" alt="A Customer Agent Performance report for the last 30 days, generated by the Internal Agent" width="2666" height="2094" data-path="snippets/reporting.png" />
</Frame>

### In your ticketing system

Your Customer Agent works as a team member in your ticketing system, so your existing reports track it automatically: SLAs, CSAT surveys, agent-level dashboards. We can also share report templates with the key metrics we recommend for every supported system.

***

Each proposal starts the next build. See [Build](/internal-agent/build).