Releasesby GlyphSemantic search for Zendesk Support ticket comments
Agents can search Zendesk Support by meaning, including ticket comment text, with each result carrying its ticket's title, status, and priority.
Also shipped Aug 13, 2026Airbyte in August 2026 →
BigQuery pipelines add automated metadata enrichment in preview
Semantic metadata defined in SQLX configurations now syncs with Knowledge Catalog, and the Data Engineering Agent can generate this metadata from your intent or context.
Sharing tables backed by default storage will be enabled by default for all accounts
OpenSharing support for tables backed by default storage is generally available and on by default for most accounts. For most Enterprise or Premium tier accounts, Databricks will enable it automatically in mid-September 2026, and by early 2027 for the rest.
Expanded networking billing for OpenSharing SecureConnect
Databricks will be expanding networking billing for OpenSharing SecureConnect. Today, data providers are billed for data transfer (egress) when recipients access shared data through SecureConnect. Additional charge types and access scenarios, including charges billed to recipients, are planned.
OpenSharing SecureConnect will be available by default for all accounts
OpenSharing SecureConnect is generally available and available by default for accounts on the Premium plan. For accounts on the Enterprise plan, Databricks will enable it automatically in mid-September 2026, and by early 2027 for the rest.
Block or redact sensitive data in requests and responses
The Sensitive Data Detection guardrail (Beta) detects structured sensitive data (such as Social Security numbers, credit card numbers, IBANs, and phone numbers) and either blocks the interaction or redacts the matched values in place.
Smart Routing: Cut AI costs by routing each task to the right model
Smart Routing (Beta) automatically picks the right model and agent harness for each task, based on complexity, permissions, and budget. It shifts routine work to lower-cost models and reserves frontier models for hard problems, and every routing decision is visible and auditable.
More from AirbyteEvery Airbyte release →
Connector setup opens the form before the AI setup assistant
New source or destination setup now opens the configuration form first, with an Agent/Form toggle to switch to the AI assistant.
Agents can join data from multiple connectors in one query
Agents can combine data from more than one connector in a single query against synced data.
Agents chat asks clarifying questions on ambiguous requests
For ambiguous requests, chat asks a short clarifying question with options; users can pick, answer, or skip.
Airbyte Self-Managed 2.2 released, one-way database upgrade
Airbyte 2.2 migrations drop tables that 2.1.x depends on, so the upgrade is one-way and rolling back to 2.1.x is not supported. Take a database backup before upgrading.
Airbyte 2.2 community deployments drop HTTP Basic API credentials
Community deployments no longer accept HTTP Basic credentials on the API. Callers must switch to an access token from /api/v1/applications/token.
Airbyte 2.2 Helm charts accept namespaceOverride
Both the main chart and the data plane chart accept a top-level namespaceOverride value that controls the namespace written onto chart resources.
Airbyte 2.2 sizes replication orchestrator separately from jobs
The server reads global.workloads.resources.replication settings for the replication orchestrator, and global.jobs.resources is deprecated in favor of global.workloads.resources.mainContainer.
Semantic search for GitHub issues, pull requests and comments
Agents can search GitHub by meaning, including issue descriptions, pull request descriptions, and comments.