The following are the release notes for TetraScience AI Services versions 1.3.x. TetraScience AI Services empower developers and scientists to transform data into decisions through seamless, secure APIs, and enable intelligent automation across scientific, lab, and enterprise workflows.

📘

NOTE

TetraScience AI Services are currently part of a limited availability release and must be activated in coordination with TetraScience along with related consuming applications. For more information, contact your customer account leader.

v1.3.0

Release date: 3 September 2026 (updated 18 September 2026)

TetraScience has released TetraScience AI Services version 1.3.0 on 3 September 2026. This release introduces AI Services telemetry, which lets data apps and agents send OpenTelemetry (OTLP) traces to AI Services and read those traces back with a standard MLflow client. It also includes a fix for AI Workflow installations that could remain stuck in a running state.

Here are the details for what's new in TetraScience AI Services v1.3.0.

Prerequisites

TetraScience AI Services v1.3.0 requires the following:

• Tetra Platform v4.4.1 or later
• For publishing "Bring Your Own Model" (BYOM) AI workflows under private-* namespaces: Tetra Platform v4.5.3 or later and TetraScience CLI (ts-cli) v2.1.0 or later

New Functionality

New functionality includes features not previously available in TetraScience AI Services.

AI Services Telemetry

AI Services now accepts operational telemetry from data apps and AI agents, and serves it back for analysis and evaluation. This gives developers visibility into how their AI workflows actually behave in an environment, covering request latency, throughput, tool-call flow, and outcome, without needing direct access to the underlying trace store.

Telemetry has two planes:

• Write plane: New OpenTelemetry Protocol (OTLP) endpoints under /ai-platform/v1/telemetry/v1/ accept trace, log, and metric data from data apps and agents, and record traces in MLflow trace format.
• Read plane: A trace-search endpoint serves the MLflow tracing REST API directly, so an unmodified mlflow or mlflow-skinny client can read an organization's traces using only a TDP JSON Web Token (JWT). Clients configure the tracking URI, host, and token; no plugin or custom client code is required. Reads are organization-scoped, and every read is audited.

Because a standard MLflow client cannot attach an arbitrary header, the read plane also accepts the organization slug as a URL path segment, so a stock client can select its organization through the tracking host alone. The header form continues to work unchanged. A request whose path and header specify different organizations is rejected.

For setup instructions, see AI Observability and Telemetry in the TetraScience AI Services User Guide (v1.3.x). For per-endpoint request and response schemas and the full status-code list, see the Telemetry API Reference.

AI Services telemetry is a limited availability release. It is controlled per organization behind a feature flag and must be enabled in coordination with TetraScience, which also provisions the telemetry destination for your organization. For more information, contact your customer account leader.

Enhancements

Enhancements are modifications to existing functionality that improve performance or usability, but don't alter the function or intended use of the system.

• There are no enhancements in this release.

Bug Fixes

The following bugs are now fixed.

• AI Workflow installations no longer remain in a running state after the underlying Databricks job has already succeeded. AI Services now periodically reconciles in-flight installations against Databricks job status and completes them when the job reports success, so BYOM and API-driven installations no longer appear stuck.

Deprecated Features

There are no deprecated features in this release. For more information about Tetra Platform deprecations, see Tetra Product Deprecation Notices.

Known and Possible Issues

The following are known limitations of TetraScience AI Services v1.3.0:

• Telemetry Sink SQL Warehouse Is Fixed at Creation: A provisioned telemetry sink's SQL warehouse can't be changed after the sink is created. To use a different warehouse, contact TetraScience to provision a new sink.
• Sink Change History Isn't Tracked: A sink record shows who created it, but not who has changed its configuration since.
• Trace Search Isn't Bounded by Time: A trace search request isn't bounded by a time range, so a search can return traces across the full history of a sink. Result counts are capped, and you can narrow results by filtering on time in your query.
• Model Training UI Upload Failure: The Upload Supporting Files button in the AI Services UI does not work for model training workflows. File uploads fail because of an incorrect S3 file path constructed by the UI. As a workaround, upload model training files and initiate model training by using the AI Services API directly. The related cross-origin (CORS) error was fixed in Tetra Platform v4.6.0.
• Analyst Policy Install Workflow UI Access: On Tetra Platform v4.4.1, users assigned a role with an Analyst policy can view, but not use, the Install Workflow button even though the policy doesn't allow them to install an AI workflow or run an inference. This issue is fixed in Tetra Platform v4.4.2 and later.
• Vector Store Deletion Does Not Remove Databricks Resources: Deleting a vector store removes the internal database record, but the associated Databricks vector search endpoint and index, the Delta tables, and the knowledge base files in Amazon S3 are not removed and require manual cleanup. Contact TetraScience Support to remove the orphaned resources. (Added on 18 September 2026)
• Vector Store Update Status Remains syncing After a Re-index Job Completes: After a vector store update is triggered, the status returned by the vector store API might remain syncing even after the re-index job completes successfully. The updated content is indexed and queryable, but because the status doesn't transition back to ready, any automated process that polls the status to confirm completion can wait indefinitely. To verify that an update completed, query the vector store and confirm that the results reflect the updated content. TetraScience is working with the vendor on a fix.
• No telemetry deprovisioning path: There is no supported way to remove a provisioned telemetry sink. Contact TetraScience Support before removing a telemetry sink.

Upgrade Considerations

To upgrade to the latest AI Services version, see Update the AI Services UI version in the TetraScience AI Services User Guide.

After the upgrade, verify the following:

• Existing AI Workflow installations continue to function correctly
• Inference requests complete successfully
• Knowledge base and vector store operations function as expected
• Asset promotion completes successfully for models, volumes, and aliases
• Telemetry writes and trace read-back complete successfully, if telemetry has been enabled for your organization
• The AI Services UI displays correctly

GxP Impact Assessment

All new TetraScience AI Services functionalities go through a GxP impact assessment to determine validation needs for GxP installations.

Enhancements and Bug Fixes do not generally affect Intended Use for validation purposes.

TetraScience AI Services is currently a limited availability release, and Model Promotion is a beta release. AI Services telemetry is part of that limited availability release. Items marked as either a beta release or a limited availability release are not validated for GxP by TetraScience. However, customers can use these prerelease features and components in production if they perform their own validation.

📘

Security

TetraScience continually monitors and tests the codebase to identify potential security issues. Security updates are applied on an ongoing basis.

📘

Quality Management

TetraScience is committed to creating quality software. Software is developed and tested following the ISO 9001-certified TetraScience Quality Management System.

For instructions on how to validate core AI Services functionality programmatically, see Test TetraScience AI Services Programmatically in the TetraConnect Hub. For access, see Access the TetraConnect Hub.

For more information, see the TetraScience AI Services documentation.

Other Release Notes

To view other TetraScience AI Services release notes, see TetraScience AI Services Release Notes.