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

# Getting started

> Connect your sources and run your first investigation.

Investigations get better the more context they can draw on. Connecting your sources takes a few minutes each, and you can start with whichever you have to hand. Every source you add makes investigations more grounded.

Everything below is configured from the [Investigations settings](https://app.incident.io/~/investigations) in your dashboard.

## 1. Connect your sources

<Steps>
  <Step title="Past incidents">
    Let investigations find similar incidents from your history and the fixes that worked before. See [Past
    incidents](/investigations/connect/past-incidents).
  </Step>

  <Step title="Channels">
    If you use Slack, add the channels where your team shares deploys, config changes, and incident context. See [Slack
    channels](/investigations/connect/slack). Connecting channels as a source is available for Slack only.
    Investigations in Microsoft Teams still read their own incident channel, but can't draw on other channels.
  </Step>

  <Step title="Documentation">
    Sync your runbooks and reference docs from Confluence, Notion, GitHub, or GitLab. See
    [Documentation](/investigations/connect/documentation).
  </Step>

  <Step title="Code repositories">
    Connect GitHub or GitLab so investigations can link relevant pull requests and read your code. See [Code
    setup](/investigations/connect/code/overview#setup).
  </Step>

  <Step title="Telemetry">
    Connect the observability tools your team uses during incidents. See
    [Telemetry](/investigations/connect/telemetry/overview).
  </Step>
</Steps>

<Tip>
  Connect the dashboards and data sources your team actually reaches for during an incident. The closer they reflect
  your real workflow, the more useful investigations will be.
</Tip>

## 2. Choose when investigations run

Decide whether investigations run for every incident, only when conditions are met, when a workflow triggers them, or only on demand. See [Triggering investigations](/investigations/triggering) for the options.

## 3. Run your first investigation

Create a test incident and trigger an investigation to see it in action. In Slack, use `/inc investigate` in the incident channel. Otherwise, set investigations to run automatically or trigger one from a [workflow](/investigations/triggering).

## What's next

* **See what an investigation can read**: the conversation, the call, shared files, and your incident's own details. See [What we can see](/investigations/what-we-can-see).
* **Understand how we measure it**: how we grade investigations for accuracy and use it to keep improving them. See [Measuring accuracy](/investigations/measuring-accuracy).
* **Try the chatbot**: tag `@incident` in an incident channel to ask about logs, code changes, past incidents, or recent deploys. See the [chatbot docs](/ai/at-incident).
* **Share feedback**: use the thumbs up/down buttons on investigation messages, and tell us what's working and what isn't.