# August 2026

> August 2026 - Read the August 2026 Managed AI Platform release notes.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-09-30T19:40:40.898378+00:00` (UTC).

## Primary page

- [August 2026](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md): Full documentation for this topic (Markdown sidecar).

## Sections on this page

- [Agentic AI](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#agentic-ai): In-page section heading.
- [Schedule automatic file refreshes in File Registry](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#schedule-automatic-file-refreshes-in-file-registry): In-page section heading.
- [Adversarial Swarm Evaluation](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#adversarial-swarm-evaluation): In-page section heading.
- [Batch agent evaluation in the DataRobot experimentation plugin](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#batch-agent-evaluation-in-the-datarobot-experimentation-plugin): In-page section heading.
- [Windows support for the Agentic Starter template](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#windows-support-for-the-agentic-starter-template): In-page section heading.
- [Data](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#data): In-page section heading.
- [Support for Salesforce connector added](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#support-for-salesforce-connector-added): In-page section heading.
- [JDBC connector now supports Amazon Redshift](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#jdbc-connector-now-supports-amazon-redshift): In-page section heading.
- [MLOps and predictions](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#mlops-and-predictions): In-page section heading.
- [Real-time build logs for execution environments](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#real-time-build-logs-for-execution-environments): In-page section heading.
- [Code-first](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#code-first): In-page section heading.
- [Python client v3.19](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#python-client-v319): In-page section heading.
- [DataRobot REST API v2.48](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/august2026-announce.html.md#datarobot-rest-api-v248): In-page section heading.

## Related documentation

- [AI Platform releases](https://docs.datarobot.com/en/docs/release/index.html.md): Linked from this page.
- [Managed AI Platform releases](https://docs.datarobot.com/en/docs/release/cloud-history/index.html.md): Linked from this page.
- [2026 Managed AI Platform releases](https://docs.datarobot.com/en/docs/release/cloud-history/2026-announce/index.html.md): Linked from this page.
- [Self-Managed AI Platform release notes](https://docs.datarobot.com/en/docs/release/archive-release-notes/index.html): Linked from this page.
- [File Registry documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/file-registry.html.md#schedule-file-refreshes): Linked from this page.
- [Adversarial Swarm Evaluation](https://docs.datarobot.com/en/docs/agentic-ai/agent-assist/agent-assist-skill.html.md#adversarial-swarm-evaluation): Linked from this page.
- [DataRobot experimentation plugin](https://docs.datarobot.com/en/docs/agentic-ai/cli/local-experimentation/index.html.md): Linked from this page.
- [Batch agent evaluation](https://docs.datarobot.com/en/docs/agentic-ai/cli/local-experimentation/experimentation-evaluation.html.md): Linked from this page.
- [Windows prerequisites](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#windows-prerequisites): Linked from this page.
- [documentation](https://docs.datarobot.com/en/docs/reference/data-ref/connectivity/data-sources/dc-salesforce.html.md): Linked from this page.
- [View build logs](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-environment-workshop/nxt-add-custom-env.html.md#view-build-logs): Linked from this page.
- [Python client changelog](https://docs.datarobot.com/en/docs/api/reference/changelogs/py-changelog/index.html.md): Linked from this page.
- [REST API changelog](https://docs.datarobot.com/en/docs/api/reference/changelogs/rest-changelog/index.html.md): Linked from this page.

## Documentation content

August 2026

This page provides announcements of newly released features available in DataRobot's multi-tenant SaaS AI Platform, with links to additional resources. From the release center, you can also access past announcements and [Self-Managed AI Platform release notes](https://docs.datarobot.com/en/docs/release/archive-release-notes/index.html).

## Agentic AI

### Schedule automatic file refreshes in File Registry

You can now schedule automatic refreshes for files added to File Registry from Browse data or a URL; files uploaded locally aren't eligible for scheduling. When you create a schedule by setting a start date and cadence, DataRobot will refresh the file automatically going forward. Expand Scheduling to manage existing schedules—pause, edit, or delete a schedule, and check its status at a glance from a status badge.

File Registry also replaces the file detail's + Add files menu with a consolidated Actions menu, where you can convert a file to a folder, link it to a Use Case, download, share, tag, or delete it. Additionally, JSON files previewed from Jira and Confluence sources now render as an expandable tree instead of an escaped string.

For more information, see the [File Registry documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/file-registry.html.md#schedule-file-refreshes).

### Adversarial Swarm Evaluation

[Adversarial Swarm Evaluation](https://docs.datarobot.com/en/docs/agentic-ai/agent-assist/agent-assist-skill.html.md#adversarial-swarm-evaluation) is now available in the [Agent Assist skill](https://docs.datarobot.com/en/docs/agentic-ai/agent-assist/agent-assist-skill.html.md) experience. After you code an agent, you can battle-test the implementation before deploy: a swarm runs attack, behavior, and persistence tracks against the agent, proposes patches for breaches, retests until scenarios pass or the fixing limit is reached, and writes `eval_report.md`. Choose the battle-test option after coding, or ask in natural language (for example, "Battle-test my agent"). For details, see [Adversarial Swarm Evaluation](https://docs.datarobot.com/en/docs/agentic-ai/agent-assist/agent-assist-skill.html.md#adversarial-swarm-evaluation).

### Batch agent evaluation in the DataRobot experimentation plugin

The [DataRobot experimentation plugin](https://docs.datarobot.com/en/docs/agentic-ai/cli/local-experimentation/index.html.md) ( `dr xp`) now supports batch agent evaluation for projects that include the [evaluation component](https://github.com/datarobot-community/af-component-evaluation). Each run sends test prompts to the agent's OpenAI-compatible endpoint and scores every response using the [NeMo Evaluator](https://github.com/NVIDIA-NeMo/evaluator) BYOB (Bring Your Own Benchmark) framework—no deployment to the platform required.

Enable the workflow with the `--enable-evaluation` flag (or `DR_EXPERIMENT_ENABLE_EVALUATION=true`), then select a pipeline, dataset, and agent endpoint from the new Evaluation tab to start a run. Eight benchmarks are available out of the box, covering answer quality, safety refusal, RAG faithfulness, and more; five of them run judge-free.

For more information, see [Batch agent evaluation](https://docs.datarobot.com/en/docs/agentic-ai/cli/local-experimentation/experimentation-evaluation.html.md).

### Windows support for the Agentic Starter template

The [DataRobot Agentic Starter application template](https://github.com/datarobot-community/datarobot-agent-application) now supports Windows, in addition to macOS and Linux. Previously, Windows developers had to fall back on a DataRobot codespace, WSL, or a virtual machine to work with the template.

On Windows, complete the [Windows prerequisites](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#windows-prerequisites) —enabling Git symlink support and granting permission to create symlinks—before cloning the repository or running `dr start`. Once configured, the rest of the installation, quickstart, and development workflow matches macOS and Linux, including PowerShell commands for installing the prerequisite tools.

For more information, see [Install prerequisite tools](https://docs.datarobot.com/en/docs/agentic-ai/agentic-develop/agentic-get-started.html.md#install-prerequisite-tools).

## Data

### Support for Salesforce connector added

This release introduces a Salesforce connector, allowing you to connect to and ingest structured data directly from Salesforce. For information on configuring a Salesforce connection, see the [documentation](https://docs.datarobot.com/en/docs/reference/data-ref/connectivity/data-sources/dc-salesforce.html.md).

### JDBC connector now supports Amazon Redshift

The JDBC connector now supports query execution to read data from Amazon Redshift, providing low-latency, and therefore faster, previews for supported data stores. You can now also access Redshift in Talk to my Data applications using the data connector integration. This change requires no additional setup.

## MLOps and predictions

### Real-time build logs for execution environments

Execution environments now include a Builds logs tab that streams build output in real time, so you can monitor a build's progress or troubleshoot a failed build without waiting for it to finish or refreshing the page. Navigate to Registry > Environments, select an environment, and open the Builds logs tab, or click View log from the Overview tab.

Select an environment version, then choose Logs to watch build output stream live, or Standard output to view the complete build output once a build finishes. For versions built before this release, build output is available only under Standard output.

For more information, see [View build logs](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-environment-workshop/nxt-add-custom-env.html.md#view-build-logs).

## Code-first

### Python client v3.19

Python client v3.19 is now generally available. For a complete list of changes introduced in v3.19, see the [Python client changelog](https://docs.datarobot.com/en/docs/api/reference/changelogs/py-changelog/index.html.md).

### DataRobot REST API v2.48

DataRobot's v2.48 for the REST API is now generally available. For a complete list of changes introduced in v2.48, see the [REST API changelog](https://docs.datarobot.com/en/docs/api/reference/changelogs/rest-changelog/index.html.md).

All product and company names are trademarks™ or registered® trademarks of their respective holders. Use of them does not imply any affiliation with or endorsement by them.
