Contextual Policies in Omnigent: Using session state to better govern AI agents
Summary
Omnigent now offers contextual policies for AI agents, enabling session state tracking to evaluate whether subsequent actions should proceed. These policies, applicable across any agent Omnigent wraps, allow for more powerful governance like per-session spending caps or risk-accumulating guardrails.
Summary generated by brickster.ai. For the full article, follow the source link above.
Topics
More from Databricks Blog
Unlocking Data Portability: Preventing Catalog Lock-in with REGISTER and UNREGISTER APIs
The new REGISTER and UNREGISTER APIs provide a standard method to safely transfer open table format management between catalogs without copying data stored in customer-owned buckets. By requiring the original catalog to explicitly relinquish control before a transfer, this workflow prevents catalog lock-in and eliminates dangerous split-brain scenarios.
In Capital Markets, the Buy Side Runs on NAV. Finance Protects the Fee.
Databricks Genie One introduces an AI coworker for asset management finance that leverages backend agents to automate NAV reconciliation and fund data ingestion across a governed business ontology. Designed to protect net fee margins under strict regulatory standards like Form PF and GIPS, it provides finance teams with real-time, traceable morning NAV calculations and audit-ready proof for every valuation.
How to choose your first Genie Agents for maximum impact
Rank candidate Genie Agent workflows in minutes using a five-criteria rubric across impact, demand, data readiness, scope, and governance to ensure adoption scales rather than stalls. Field examples demonstrate how to apply this framework in practice to classify use cases into build now, shape it first, and hold off categories.
Real-Time Retail Intelligence: Building E-Commerce Recommendations with Lakebase and AI Search on Databricks
A complete reference architecture is now available for building a real-time, multi-stage e-commerce recommendation engine on Databricks using AI Search for candidate retrieval, Lakebase for online feature serving, and Model Serving for low-latency inference. By unifying batch precomputation and real-time scoring on a single governed platform, this design replaces fragmented ML stacks to eliminate glue code and deliver end-to-end lineage from raw clickstream to production predictions.
How Genie One reshapes work for finance teams
Genie One delivers a business-context-grounded AI coworker that helps finance teams analyze performance, model scenarios, investigate variances, and accelerate forecasting and reporting. The tool enforces consistent guardrails across data access, actions, and AI usage to ensure every interaction remains auditable, permission-aware, and within organizational controls.
Read Restrictions and Catalog Labels: Unifying governance across engines and catalogs
Apache Iceberg has introduced read restrictions and catalog labels, two new specifications designed to standardize policy enforcement across different engines and catalogs. These additions eliminate fragmented enforcement by delegating access decisions to trusted engines and making governance metadata portable across federated catalogs.