Databricks shows durable loan-agent workflow with Temporal
Databricks has published a reference design for a loan-approval agent that can survive interruptions and hand off work between cloud systems. It uses Temporal for tracking what’s done, and Lakebase Postgres for storing records, helping operations tolerate crashes or process failures. Policy rules from Unity Catalog sync automatically. The design lets underwriters pause a case and pick up later, without losing progress or audit data.
- Reference design uses Temporal and Lakebase Postgres
- Workflow survives worker or deployment failures
- Policy rules update without deployment via Unity Catalog
- All steps and evidence are auditable for each loan
- System pauses safely while waiting for a human
Sources covering this
More in Enterprise
Red Hat adds NVIDIA BlueField to OpenShift
Red Hat OpenShift will now support NVIDIA BlueField hardware, aiming to make data centers faster by letting specialized cards take on tasks usually handled by main processors. By moving network traffic management and security enforcement off CPUs and onto BlueField, businesses can free up computing power for core applications and AI tasks. Red Hat says this helps cut operational costs and makes network security more robust.
Google Cloud launches Data Agent Kit for analytics
Google Cloud has introduced the Data Agent Kit, a set of tools meant to speed up analytics by letting developers run data investigations directly inside their code editor. Instead of switching between different systems and writing manual queries, users can ask questions in plain language and get automated workflows that assemble and run the right database queries. The kit works with IDEs like VS Code forks and aims to ease multi-tool data hunts.
Google Data Cloud adds new AI and analytics tools
Google just launched several new features for its Data Cloud. BigQuery now supports stateful processing in streaming queries, letting you do things like rolling averages in real time (currently in preview). There’s also a ready-to-use synthetic data generator for Managed Kafka, now generally available. And Lakehouse managed tables for Apache Iceberg are in preview, promising easier data management and cross-tool compatibility. Updates to Dataflow pipelines are also rolling out.
GitLab Duo Self-Hosted supports multiple AI models via Azure
GitLab is letting organizations use its AI coding features with their own choice of large language models, including OpenAI, Anthropic, Meta, and Mistral, when deployed through Microsoft’s Foundry platform on Azure. Companies can now pick which region, network, and cloud controls handle their code—with model assignments down to the individual feature. This helps teams meet data residency and compliance needs.