---
title: AI Investigations
description: >-
  Datadog's agentic investigations bring structured, first-pass root-cause
  analysis directly into your RUM workflows.
breadcrumbs: Docs > RUM & Session Replay > AI Investigations
---

# AI Investigations

## Overview{% #overview %}

Investigating poor user experience in RUM typically means switching between session replays, error panels, traces, and performance timelines to piece together what went wrong. AI Investigations automate that first-pass triage. Datadog's RUM agent inspects the data attached to your views and surfaces ranked, categorized root-cause findings directly in your RUM workflow.

This page lists the available investigation types.

## Single-view AI investigation{% #single-view-ai-investigation %}

Run an agentic investigation on a single RUM view to investigate performance issues or identify optimization opportunities on that specific page or screen. Datadog's RUM agent inspects the view event and its sub-events to identify root causes from sources spanning the application, the backend, third-party libraries, and the user's network environment.

{% image
   source="https://docs.dd-static.net/images/real_user_monitoring/ai_investigations/single-view-ai-investigation-overview.3aa0bda607e8dc9203d4c521123dcfc9.png?auto=format&fit=max&w=850 1x, https://docs.dd-static.net/images/real_user_monitoring/ai_investigations/single-view-ai-investigation-overview.3aa0bda607e8dc9203d4c521123dcfc9.png?auto=format&fit=max&w=850&dpr=2 2x"
   alt="A Single-View AI Investigation surfacing root cause findings for a RUM view." /%}

For more information, see [Single-View AI Investigation](https://docs.datadoghq.com/real_user_monitoring/ai_investigations/single_view_ai_investigation.md).

## Multi-view AI investigation{% #multi-view-ai-investigation %}

Run an agentic investigation across a sample of views that share a slow performance vital. Multi-View AI Investigation extends the same agentic analysis to a population of views, helping you identify what to fix when an entire (view × vital) pair is consistently slow across users. Available from the Optimization page for Loading Time, Largest Contentful Paint, First Contentful Paint, and Interaction to Next Paint.

{% image
   source="https://docs.dd-static.net/images/real_user_monitoring/ai_investigations/multi-view-ai-investigation-recommendations.b9c0773905eb00d282c65caf93e7b8e1.png?auto=format&fit=max&w=850 1x, https://docs.dd-static.net/images/real_user_monitoring/ai_investigations/multi-view-ai-investigation-recommendations.b9c0773905eb00d282c65caf93e7b8e1.png?auto=format&fit=max&w=850&dpr=2 2x"
   alt="The Optimization page for a performance vital, showing ranked recommendation cards with an Investigate button on each." /%}

For more information, see [Multi-View AI Investigation](https://docs.datadoghq.com/real_user_monitoring/ai_investigations/multi_view_ai_investigation.md).

## Operation AI investigation{% #operation-ai-investigation %}

Run an agentic investigation on a single operation in [Operations Monitoring](https://docs.datadoghq.com/real_user_monitoring/operations_monitoring.md). The agent analyzes both the success rate and the latency of the operation, surfacing focused investigations for each failure mode (errors, timeouts, abandonment) and for latency regressions.

{% image
   source="https://docs.dd-static.net/images/real_user_monitoring/ai_investigations/operation-ai-investigation-recommendations.f5180e12529a8e14d50821de996258f7.png?auto=format&fit=max&w=850 1x, https://docs.dd-static.net/images/real_user_monitoring/ai_investigations/operation-ai-investigation-recommendations.f5180e12529a8e14d50821de996258f7.png?auto=format&fit=max&w=850&dpr=2 2x"
   alt="The Operations page for an operation, showing a plain-language health summary and ranked recommendation cards tagged with priority badges." /%}

For more information, see [Operation AI Investigation](https://docs.datadoghq.com/real_user_monitoring/ai_investigations/operation_ai_investigation.md).

## Further reading{% #further-reading %}

- [Learn about the RUM Explorer](https://docs.datadoghq.com/real_user_monitoring/explorer.md)