provider AI observabilityllm_analytics POST /api/environments/{environment_id}/llm_analytics/evaluation_summary/
@utdk/posthog /api/environments/{environment_id}/llm_analytics/evaluation_summary/
environments_llm_analytics_evaluation_summary_create
Generate an AI-powered summary of evaluation results. This endpoint analyzes evaluation runs and identifies patterns in passing and failing evaluations, providing actionable recommendations. Data is fetched server-side by evaluation ID to ensure data integrity. **Use Cases:** - Understand why evaluations are passing or failing - Identify systematic issues in LLM responses - Get recommendations for improving response quality - Review patterns across many evaluation runs at once
environment_id path required
Deprecated. Use /api/projects/{project_id}/ instead.
string

Try it

Authentication
Configure credentials for PostHog API
environmentsLlmAnalyticsEvaluationSummaryCreate
POST/api/environments/{environment_id}/llm_analytics/evaluation_summary/
Generate an AI-powered summary of evaluation results. This endpoint analyzes evaluation runs and identifies patterns in passing and failing evaluations, providing actionable recommendations. Data is fetched server-side by evaluation ID to ensure data integrity. **Use Cases:** - Understand why evaluations are passing or failing - Identify systematic issues in LLM responses - Get recommendations for improving response quality - Review patterns across many evaluation runs at once

Parameters

required

Deprecated. Use /api/projects/{project_id}/ instead.

Input

required

UUID of the evaluation config to summarize

Filter type to apply ('all', 'pass', 'fail', or 'na') * `all` - all * `pass` - pass * `fail` - fail * `na` - na

Optional: specific generation IDs to include in summary (max 250)

If true, bypass cache and generate a fresh summary

Configure credentials above to enable sending.

Code snippet
Updates live as you fill in the form above.

TypeScript

import posthog from '@utdk/posthog';

await posthog.environmentsLlmAnalyticsEvaluationSummaryCreate({
  "filter": "all",
  "force_refresh": false
})