> AI agents: this is one page from PostHog's docs. Full index of Markdown docs for LLMs: https://posthog.com/llms.txt # Evaluation reports Canonical URL: https://posthog.com/docs/ai-evals/reports > **Cloud region:** This page uses US Cloud hosts. For an EU Cloud project, use `https://eu.posthog.com` instead of `https://app.posthog.com` (app host for links). ## On this page - [Default report configuration](#default-report-configuration) - [Report metrics by evaluation type](#report-metrics-by-evaluation-type) - [Customizing reports](#customizing-reports) Evaluation reports summarize your [evaluation](https://posthog.com/docs/ai-evals.md) results over time and send them to email or Slack, so you can track quality without reading every result. PostHog creates a default report configuration for every evaluation you make. Reports are available for all evaluation types – **LLM-as-a-judge**, **code-based**, and **sentiment analysis** – on any target. Reports also power [Self-driving](https://posthog.com/docs/ai-observability/self-driving.md#eval-reports). Turn on the **AI observability** source in your [inbox](https://app.posthog.com/inbox) settings, and report findings arrive as signals. ## Default report configuration The auto-created report uses these defaults: | Setting | Default value | Description | | --- | --- | --- | | **Frequency** | Count-based | Generates a report after a set number of evaluation runs | | **Trigger threshold** | 100 | A report is generated every 100 new evaluation results | | **Cooldown** | 1 hour | Minimum hours between count-triggered reports (1 – 24 hours) | | **Daily run cap** | 10 | Maximum report runs per day | | **Enabled** | Yes | Reports start generating immediately | | **Delivery targets** | None | Reports are viewable in the UI but no notifications are sent | Reports are viewable directly in the evaluation's **Reports** tab without configuring any delivery targets. ## Report metrics by evaluation type Reports display different metrics depending on your evaluation's output type: - **Boolean evaluations** (LLM-as-a-judge and code-based) – Pass rate, pass/fail/N/A counts, total runs, and comparison to the previous reporting period - **Numeric score and categorical evaluations** – Pass rate and pass/fail/N/A counts, based on the evaluation's passing rule. Reports need a passing rule. - **Sentiment analysis evaluations** – Positive, neutral, and negative counts with distribution percentages, total runs, and comparison to the previous reporting period ## Customizing reports You can adjust the report configuration after creating an evaluation: - Change the trigger threshold to generate reports more or less frequently - Adjust the minimum hours between reports (1 – 24) to control how often count-triggered reports can fire - Add email or Slack delivery targets to receive notifications when reports are generated - Disable the report if you don't need automated summaries