---
title: "Public Preview: Multi-turn evaluation in Microsoft Foundry — Cloud Changelog"
description: "Multi-turn evaluation is now in public preview in Microsoft Foundry. You can assess complete agent conversations against your quality standards, not only…"
url: "https://cloudchangelog.com/azure/581746"
updated: "2026-11-20"
---

[Back to feed](https://cloudchangelog.com/feed/2026-W47)

November 20, 2026 · AzureIn preview

# Public Preview: Multi-turn evaluation in Microsoft Foundry

- [Microsoft Foundry](https://cloudchangelog.com/products/azure/microsoft-foundry)
- [AI and machine learning](https://cloudchangelog.com/search?q=ai-ml)

Multi-turn evaluation is now in public preview in Microsoft Foundry. You can assess complete agent conversations against your quality standards, not only individual responses.

A response can look correct on its own and still be part of a conversation that fails the user. For example, an agent can repeat the same failing action across several turns and leave the request unresolved. Turn-level scores do not show this pattern.

With multi-turn evaluation, you set the evaluation level of a run to score each turn or the conversation as a whole. Conversation-level evaluators, such as task completion, customer satisfaction, coherence, groundedness and tool use quality, find problems like incomplete task resolution, user frustration and tool-call regressions. You provide conversation data as JSONL with a full `messages` array, including tool calls and tool definitions, and run the evaluation with the Foundry SDK.

[Learn more](https://learn.microsoft.com/azure/foundry/observability/how-to/cloud-evaluation-conversations).

Get changes like this in your inbox

Your email address

Free, every Monday: what changed across AWS, Google Cloud, Azure, Cloudflare and the AI providers. We email you a link to confirm.

Free. Unsubscribe any time.

[Read on azure.microsoft.com](https://azure.microsoft.com/updates?id=581746)

## Related updates

- Jun 3, 2026

  [Public Preview: Rubric evaluator in Microsoft Foundry](https://cloudchangelog.com/azure/563656)
- Jun 3, 2026

  [Public Preview: Evaluations with Intelligent Trace Sampling](https://cloudchangelog.com/azure/563696)
- Nov 18, 2025

  [Public Preview: Microsoft Foundry Fine-Tuning Updates](https://cloudchangelog.com/azure/526742)
- Mar 31, 2026

  [Amazon Bedrock AgentCore Evaluations is now generally available](https://cloudchangelog.com/a/2026-03-agentcore-evaluations-generally-available) · AWS
- Apr 17, 2025

  [Amazon Bedrock RAG and Model Evaluations now support custom metrics](https://cloudchangelog.com/a/2025-04-amazon-bedrock-rag-model-evaluations-custom-metrics) · AWS

[All Microsoft Foundry changes](https://cloudchangelog.com/products/azure/microsoft-foundry)

## Contact

- [YouTube](https://www.youtube.com/@cloudchangelog)
