Releasesby Ibis[Improvement] Context Hub
Update10 days agoUnverifiedAdded Oct 17, 2026
The Connections page shows the status, run history, and any errors or warnings for each Fivetran connection that brings data to your agents. You can also test connections and run syncs on demand.
Topics: AI agents
More Hightouch releases
Every Hightouch release[New] AI Decisioning
When AI Decisioning schedules messages for the best time of day, you can choose the exact send time within each three-hour window. For example, send early-morning messages at 7 AM instead of 6 AM while morning messages still go out at 9 AM. Send times follow each user's time zone and apply to new recommendations.
[New] Events
New Amazon SQS event source for collecting events directly from SQS queues.
[Improvement] Destinations
When you sync users to Iterable in Update mode, you can now skip records for users who don't exist in Iterable instead of rejecting them. Skipped records don't count as rejections, so rejected-row alerts reflect only real errors.
[New] Events
Braze plugins are now available for the Hightouch browser, iOS, and Android SDKs. They pass the user updates, events, and purchases you track with Hightouch on to Braze, so you can use Braze in-app messages and Content Cards without adding separate Braze tracking.
[Improvement] Sources
Warehouse Export speeds up large syncs by having your warehouse write results straight to cloud storage. When a setup problem, such as missing bucket permissions, turns it off, Hightouch now shows that it's off and why, and you can re-enable it for a single sync or for all of a source's syncs.
[New] Sources
Snowflake sources can use a named external stage for Warehouse Export, so Snowflake writes to your storage bucket with its own access instead of temporary credentials from Hightouch. Use it if your Snowflake account blocks writes that use temporary credentials.
[Improvement] Agents
Agent responses now include citations for the definitions and assumptions behind each part of an answer. A citation appears at the end of each paragraph or list item it supports, and the full list still appears at the end of the response.
[New] Context Hub
Automatically sync images and creative files from your digital asset manager (DAM), the tool where your team stores brand assets, into your asset library. Run the sync on a schedule, or start it whenever you need fresh assets.
Also shipped on Oct 14, 2026
Hightouch in October 2026Workspace-level package repositories for Databricks Apps are generally available
Workspace admins can now configure default Python and npm package repositories for Databricks Apps. Apps inherit the workspace configuration while still allowing app-level overrides. See Configure default package repositories .
The Apache Hive catalog endpoint in the Lakehouse runtime catalog is now generally available (GA)
The Apache Hive catalog endpoint in the Lakehouse runtime catalog is now generally available (GA). This integration lets you use the metastore as a serverless, central metadata layer, enabling seamless data sharing and unified querying across Apache Spark, Apache Hive, and BigQuery.
Metadata migration from Dataproc Metastore to Lakehouse is now generally available (GA)
Metadata migration from Dataproc Metastore to Lakehouse is now generally available (GA). You can perform a one-time backfill migration or dry run to migrate metadata from a Dataproc Metastore service to an Apache Iceberg REST catalog endpoint or a Hive catalog endpoint using the Google Cloud console, the gcloud CLI, or the REST API.
Conversational analytics now lets you create a conversation with all of the data sources in multiple...
Conversational analytics now lets you create a conversation with all of the data sources in multiple projects, or create a conversation with a dataset . These features are generally available (GA).
You can publish a BigQuery Conversational Analytics agent in Gemini Enterprise
You can publish a BigQuery Conversational Analytics agent in Gemini Enterprise . This feature is now generally available (GA).
The AI.AGG function now supports the output_schema argument, which lets you specify the schema of the...
The AI.AGG function now supports the output_schema argument, which lets you specify the schema of the function output as a comma-separated list of fields. This feature is generally available (GA).