---
date: 2026-09-01
title: Build multi-message prompts and evaluate multi-modal inputs
description: Two new capabilities for LLM-as-a-Judge evaluators.
ogVideo: https://static.langfuse.com/changelog-videos/2026-09-01-multi-modal-multi-prompt.mp4
author: Tobias Wochinger
---

> **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the current documentation (https://langfuse.com/docs) and the API/SDK reference (https://api.reference.langfuse.com).

LLM-as-a-Judge evaluators now support two new capabilities:

- **LLM-as-a-Judge with multiple prompt messages:** Use a System message for the evaluation criteria, a User message for the content to evaluate, and an Assistant message to show an example result.
- **LLM-as-a-Judge with multi-modal inputs:** Evaluate images, audio, video, PDFs, or text files captured in your observations. The selected LLM-as-a-Judge model and provider must support the media type.

Either capability can be used on its own. Self-hosters can configure media delivery and size limits with the [`LANGFUSE_EVALUATOR_MEDIA_*` environment variables](/self-hosting/configuration#llm-as-a-judge-media).

## Learn more

- [Prompt message roles](/docs/evaluation/evaluation-methods/llm-as-a-judge#prompt-message-roles)
- [Multi-modality](/docs/observability/features/multi-modality#llm-as-a-judge)
- [Self-hosting configuration](/self-hosting/configuration#llm-as-a-judge-media)

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/changelog/2026-09-01-multi-message-prompts-and-multimodal-inputs.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.