> ## 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. # Investigations > Find the root cause of incidents faster, with evidence you can trust. Investigations automatically work out what's going on during an incident, doing the legwork a responder normally would — faster, and across every source at once. The moment an incident is declared, an investigation gathers context from across your stack: the alert and its stack trace, similar past incidents, Slack discussion and change events, your runbooks, recent code changes, and your telemetry. It forms a hypothesis and then tests it — reading your code and querying your dashboards to confirm or rule it out — and posts a root cause, the evidence behind it, and clear next steps into the incident channel within the first few minutes. Responders open the channel to a head start, not a blank page. ## What an investigation looks at Investigations draw on context from across your stack, combining these sources into a single picture. The more you connect, the more grounded each investigation becomes. Surface similar incidents from your history and the fixes that worked before. Pick up real-time context like deploys, config changes, and team discussion. Correlate deploys, feature flags, and config changes against when the incident started. Search your runbooks and reference docs from Confluence, Notion, GitHub, and GitLab. Identify the pull request that caused an issue and trace errors through your code. Query the logs, metrics, traces, and dashboards your team already relies on. And one source needs no setup: every investigation automatically checks whether [third-party dependencies](/investigations/third-party-dependencies) you rely on — AWS, GitHub, Stripe, and the like — were having an outage at the time. ## Where to go next Connect your sources and run your first investigation. Understand the phases an investigation moves through and how it builds findings. The context an investigation reads from inside your incident, from the conversation to call transcripts. How we grade investigations against what really caused your incidents, and use it to improve them. How investigations stay under your control, auditable, and honest about what they know. Choose when investigations run — automatically, by condition, or on demand. Set up each source, from telemetry providers to code repositories. For details on how incident.io handles your data during AI processing, see our [AI privacy guidance](https://trust.incident.io/) in the Trust Center.