# Databricks Bolsters AI Agent Governance _Databricks enhances Unity AI Gateway with guardrails, cost controls, and service policies to manage AI agents at scale._ **Updated:** 2026-08-22 **Published:** 2026-05-19 **Source:** https://www.startuphub.ai/ai-news/technology/2026/databricks-bolsters-ai-agent-governance --- Databricks is stepping up its game in the burgeoning field of AI agent management with significant updates to its [Unity AI Gateway](https://www.databricks.com/blog/whats-new-unity-ai-gateway-service-policies-guardrails-observability-and-cost-controls-ai). The platform now offers a suite of tools designed to bring much-needed structure and control to the deployment of AI agents and model-serving endpoints (MCPs). AI Agents in ProductionDriverFrom the article 9+ mentionsAs AI agents move rapidly into production, organizations face challenges in managing costs, ensuring predictable behavior, and maintaining security.addressesDatabricks Unity AI GatewayCoreplatform for managing AI agents and model-serving endpointsFrom the article 2 mentionsDatabricks is stepping up its game in the burgeoning field of AI agent management with significant updates to its Unity AI Gateway.LLM GuardrailsCoreflexible safety, compliance, and business rules using models and promptsFrom the article 3 mentionsA key addition is the introduction of LLM-based guardrails.Control AI SpendContexttools to manage and monitor AI costs effectivelyFrom the article 3 mentionsThe platform now offers a suite of tools designed to bring much-needed structure and control to the deployment of AI agents and model-serving endpoints (MCPs).Full ObservabilityContextcentralized logging of model inputs and outputs for insightsService PoliciesContextdefine rules for agent actions and interactionsFrom the article 2 mentionsAdmins can now define policies to govern how AI agents interact with tools and services.enablesEnhanced AI GovernanceEffectstructure and control for AI agents at scaleFrom the articleDatabricks aims to address these gaps with new capabilities focused on AI governance for agents.leads toPredictable AI BehaviorOutcomekeeping AI behavior within defined boundaries without disruptionFrom the article 2 mentionsAs AI agents move rapidly into production, organizations face challenges in managing costs, ensuring predictable behavior, and maintaining security. As AI agents move rapidly into production, organizations face challenges in managing costs, ensuring predictable behavior, and maintaining security. Databricks aims to address these gaps with new capabilities focused on AI governance for agents. ## Enhanced AI Safety with LLM Guardrails A key addition is the introduction of LLM-based guardrails. These are designed to be more flexible than traditional filters, allowing teams to define safety, compliance, and business-specific rules using models and prompts. These guardrails can be applied in real-time to model inputs and outputs, helping to keep AI behavior within defined boundaries without disrupting workflows. Centralized logging within Unity Catalog provides visibility into how these guardrails are functioning in production environments. ## Controlling AI Spend Unpredictable costs are a major concern as AI usage scales. Unity AI Gateway's new cost controls offer token-level attribution across requests, users, and endpoints. Teams can set per-user alerts and enforce hard budget limits to prevent runaway expenses, ensuring AI initiatives stay within financial parameters. ## Full Observability with Payload Logging Understanding agent actions is critical for debugging and compliance. Payload logging captures every request and response from model calls and MCP interactions. These logs are stored as system tables in Unity Catalog, creating a queryable record of agent activity for easier troubleshooting and auditing. ## Service Policies for Agent Actions Admins can now define policies to govern how AI agents interact with tools and services. Service policies allow granular control over which MCPs agents can invoke, based on identity and request context. This enables restrictions on accessing sensitive data or performing critical actions, ensuring agents operate within approved parameters. These new features are currently available in Beta. --- Original analysis from [startuphub.ai](https://www.startuphub.ai), the #1 AI startup directory. © StartupHub.ai. All rights reserved. You may not republish this article in full without a license. Search engines and AI research tools may crawl and summarize for reference. Bulk reproduction or model training on this content requires a license. See https://www.startuphub.ai/terms.