Back to vendors
D

Databricks Agent Bricks

Also known as: Databricks Mosaic AI, Mosaic AI, MosaicML, Mosaic AI Agent Framework

Visit site
Entry priceUsage based pricing on Databricks Units (DBUs), billed per second, after a free trial. There is no seat price.Full pricing detail

Databricks' agent platform, now sold as Agent Bricks, for building, governing and monitoring multi-agent systems on the Databricks Data Intelligence Platform.

Mosaic AI is the name Databricks used for the artificial intelligence layer of its Data Intelligence Platform, which originated with the 2023 acquisition of MosaicML. Databricks now sells the agent part of that layer as Agent Bricks, a control plane for governing, managing, and monitoring AI agents across an enterprise, and no longer uses the Mosaic AI name on its product pages or documentation.

Teams build agents two ways. Managed agents are configured rather than coded. Knowledge Assistant answers questions over a company's documents, Supervisor Agent coordinates other agents, Unity Catalog functions, MCP servers, and code execution into one system, and Genie Agents answer natural language questions over governed data. Code first agents are built with the Agent Framework in Python using common agent libraries. Agents draw on AI Search (formerly Vector Search) for retrieval, can keep long term memory per user or team in Lakebase (in beta), and are served as REST endpoints, deployed as Databricks Apps, or scheduled on recurring workflows.

For governance, Unity Catalog applies role based access to models, tools, and connections with lineage, end users reach only the agents and data they are granted, and service policies can block sensitive data, prompt injection, and unsafe content or hold a risky tool call for human approval. MLflow traces every interaction, tool call, and model call, and the same scorers and LLM judges used to compare versions run on a sample of production traffic. Admins can connect OpenAI, Anthropic, Bedrock, Gemini, and other providers with their own keys through Unity Gateway alongside hosted models.

Pricing follows Databricks consumption billing in Databricks Units on AWS, Azure, and Google Cloud, with a free trial and committed use discounts.

Vendor details

Canonical URL

https://www.databricks.com/product/artificial-intelligence/agent-bricks

Category

Multi-agent platform

Subcategory

Enterprise agent platform on Databricks (Mosaic AI)

Funding status

Agent Bricks is the agent layer of Databricks, the company used by 15,000+ organizations. It is built on Databricks' 2023 acquisition of MosaicML, sold for a time as Mosaic AI, now fully integrated across the Databricks Data Intelligence Platform.

Company status

first party product

Use cases & customers

Primary use cases

Building production tool-calling agents and RAG applications on enterprise dataMulti-agent system development with governed data accessAgent evaluation and quality assurance (AI judges + human review)Serving and governing LLMs and agents (Model Serving, AI Gateway, Unity Catalog)Domain-specific agent optimization via Agent Bricks (synthetic data + benchmarks)

Target customers

Enterprise data & AI teamsDatabricks customersML / AI engineers

Deployment options

SaaS (Databricks platform)Cloud (AWS, Azure, GCP)

Integrations

Agent Bricks is native to the Databricks Data Intelligence Platform. It connects enterprise data in Delta Lake to LLMs through AI Search (formerly Vector Search), Model Serving, Foundation Model APIs (serving OpenAI, Anthropic, and others), MLflow tracing and evaluation, and Unity Catalog governance. Tool calling agents, RAG, and multi agent systems can be authored in LangChain, LangGraph, or native Python, with a Tool Catalog for function calling and an AI Gateway governing LLMs and MCP. The platform runs on AWS, Azure, and GCP.

In practice

Your agents need enterprise data, but the data and the models live in different worlds. Agent Bricks builds agents on Databricks, where the data, models, and governance sit in one environment under Unity Catalog.

You can't tell whether your agent's output is actually good. On Databricks, MLflow scorers, which are LLM judges and code checks, grade your agent's traces and compare versions before you ship, and the same scorers run on a sample of production traffic.

Tuning an agent for cost and quality is endless manual work. Agent Bricks generates synthetic data for each task and optimizes the agent's quality against it.

Agentic Index coverage score

13.0 / 14 capabilities · 93%

Integrations & Tool Calling Full

Agents take tools from managed, external and custom MCP servers, Unity Catalog functions, Databricks data and a sandboxed code execution tool, with role based access applied to models, tools and connections.

Sourcedocs.databricks.com/agents/mcp-toolsread 2026-09-27

Workflow Orchestration Full

Supervisor Agent delegates work across Genie Agents, agent endpoints, Knowledge Assistant endpoints, Unity Catalog functions, MCP servers and custom agents and synthesizes the results, and code first multi agent systems are built with the Agent Framework.

Sourcedocs.databricks.com/aws/en/agents/agent-bricks/multi-agent-supervisorread 2026-09-27

Knowledge Grounding & RAG Full

AI Search (formerly Vector Search) is a governed vector index built into the platform that agents query for retrieval, and Knowledge Assistant builds a question answering agent over the customer's documents.

Sourcedocs.databricks.com/ai-search/ai-searchread 2026-09-27

Human Oversight & Guardrails Full

Service policies on MCP and model services can return an "ASK" decision that holds an interaction for human approval before it proceeds, such as a destructive MCP tool call, and also block PII, prompt injection and unsafe content; Supervisor Agent asks users to approve web search queries. Service policies are in beta and do not yet cover agent services.

Sourcedocs.databricks.com/data-governance/unity-catalog/service-policiesread 2026-09-27

Security, Identity & Governance Full

Unity Catalog applies role based access to models, tools and connections with lineage, end users reach only the subagents and data they are granted, and model provider credentials stay behind privileges. Compliance profiles cover HIPAA, IRAP, PCI-DSS and FedRAMP High and Moderate, with reports available through the Databricks Security and Trust Center.

Sourcedatabricks.com/product/artificial-intelligence/agent-bricksread 2026-09-27

Observability & Auditability Full

MLflow Tracing captures every interaction, tool call and model invocation of an agent with no code changes, each session shareable by link, and Unity Gateway's unified tracing adds tool and skill use to model requests under Govern > Traces.

Sourcedocs.databricks.com/mlflow3/genai/tracing/overviewread 2026-09-27

Memory & State Persistence Full

Managed agent memory, in beta, stores long term memory that persists across conversations in Lakebase, scoped per verified end user or to a team, project or organization key, with semantic search and the source session recorded, and managed sessions keep durable conversation history. It works with agents on any framework. Entries can be listed and searched, and there is no stated way to delete one user's entries.

Sourcedocs.databricks.com/aws/en/agents/agent-memory/managed-memoryread 2026-09-27

Deployment & Data Residency Full

The platform runs on AWS, Azure and Google Cloud with a published supported regions list, can be configured against the customer's own cloud account, and deploys agents to Model Serving endpoints or serverless Databricks Apps.

Sourcedocs.databricks.com/resources/supported-regionsread 2026-09-27

Prebuilt Agents, Templates & Packs Full

Named managed agents ship ready to configure. Knowledge Assistant answers questions over the customer's documents, Supervisor Agent coordinates other agents and tools, and Genie Agents answer natural language questions over governed data.

Sourcedocs.databricks.com/agentsread 2026-09-27

Triggers & Channel Coverage Full

Agents are served as REST endpoints or scheduled on recurring workflows through Lakeflow Jobs, which run without a person starting them, and Genie reaches users in Slack and on mobile.

Sourcedatabricks.com/product/artificial-intelligence/agent-bricksread 2026-09-27

Model Flexibility & Routing Full

Admins connect external providers with their own keys (OpenAI, Azure OpenAI, Anthropic, Amazon Bedrock, Microsoft Foundry, Google Gemini Enterprise or a custom provider) as Unity Catalog securables granted per user, alongside hosted DeepSeek, Llama, Gemini, Claude and GPT models, and Smart Routing defaults can be set centrally.

Sourcedocs.databricks.com/ai-gateway/model-provider-servicesread 2026-09-27

APIs, SDKs & MCP Extensibility Full

Agents are served as REST APIs, Supervisor Agents can be created programmatically with the Databricks SDK and queried through the API, Declarative Automation Bundles manage resources as code, and the Genie One MCP server, now generally available, exposes Genie to outside MCP clients under Unity Catalog permissions.

Sourcedocs.databricks.com/aws/en/agents/agent-bricks/multi-agent-supervisorread 2026-09-27

Testing, Debugging & Optimization Full

MLflow scorers, which are LLM judges and code checks, grade traces from the UI or across a dataset with mlflow.genai.evaluate() to compare app versions. The same scorers run on a sample of production traffic, and Agent Bricks generates synthetic data for each task to optimize quality.

Sourcedocs.databricks.com/mlflow3/genai/eval-monitorread 2026-09-27

Browser & Computer Use Not documented

Supervisor Agent carries a sandboxed code execution tool with no internet access and a web search tool, and agents work through APIs, data and MCP. Databricks does not describe browser control or computer use.

Sourcedocs.databricks.com/aws/en/agents/agent-bricks/multi-agent-supervisorread 2026-09-27

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Product updates

·MCP / tool calling / APIVerified

ChatGPT, Codex, Claude, Claude Code and Cursor can now connect to Databricks MCP servers, including the Genie One MCP server, with default OAuth client IDs. An account admin no longer has to create an OAuth app for each of these agents first. The feature is generally available.

Bears on: MCP / tool calling / API

View source
·Agent capabilityVerified

Databricks moved the Agent Bricks Knowledge Assistant and Supervisor Agent to legacy status. For new agents written in code it now recommends the Agent Bricks CLI, and for agents built without code it points to Genie Agents.

Bears on: Workflow orchestration

View source
·MCP / tool calling / APIVerified

Databricks released the Agent Bricks CLI in beta, which scaffolds a custom code agent from a LangGraph or OpenAI Agents SDK template, runs it locally and deploys it to the Databricks agent runtime. One config file declares the agent's tools, memory, sessions and tracing, and deployment provisions them and grants the agent's own identity access.

Bears on: Workflow orchestration

View source
View all 6 Databricks Agent Bricks updates →Tracked since Jun 2026 · Verified from public vendor sources

Pricing

Usage based pricing on Databricks Units (DBUs), billed per second, after a free trial. There is no seat price.

Consumption of Databricks Units (DBUs) for compute and Databricks Storage Units (DSUs) for storage, billed per second at price list rates that vary by cloud and product. Model APIs bill per token or by provisioned throughput.

Trial available

Included quota

There is no fixed seat price. A free trial lets teams evaluate the platform, after which usage is billed by DBU consumption across model serving, vector search, agent execution and jobs, plus per token Foundation Model API usage. Enterprise committed use contracts bundle volume at a discount. The platform runs on AWS, Azure and GCP.

What is public

Databricks publishes its consumption based model, per DBU rates by cloud and workload, and per token Foundation Model API rates. Total cost has no single figure because it depends entirely on consumption, and enterprise committed use discounts are negotiated.

Billing mechanics

Consumption billing in DBUs for compute and DSUs for storage at per second granularity, with each workload (model serving, AI Search, agent execution, jobs) metered at price list rates that vary by cloud and product. Model APIs bill per token or by provisioned throughput. Committed use contracts give discounts. When Databricks runs against the customer's own cloud account, the cloud provider bills its resources separately. Accounts not on Azure can pay monthly by card and cancel anytime.

Cost watchouts

DBU consumption spans multiple workloads (model serving, vector search, agent execution, jobs) that bill in parallel, and underlying cloud compute is billed by the cloud provider on top. Foundation Model API token costs scale with usage. Real spend is hard to predict from the rate card alone and depends on architecture and volume.

Variable cost rationale

Everything is metered by consumption. Compute bills in DBUs per second across model serving, vector search, agent execution and jobs, storage bills in DSUs, and model APIs bill per token. The bill grows with agent activity, and long running or high throughput agent systems add cost across several workloads at once. When Databricks runs in the customer's own cloud account, the cloud provider bills the underlying infrastructure separately. No cap is built in. Committed use contracts prepay volume at a discount, and provisioned throughput reserves model capacity at a steadier cost.

Additional watchouts

Consumption based billing means cost tracks usage across several workloads plus underlying cloud compute, which is billed separately. Committed use pricing is negotiated. The rate card gives no monthly figure on its own, since spend follows the DBU and token consumption of each workload.

Overage / add-ons

There are no fixed caps. Usage bills by DBU consumption and per token model usage. Committed use contracts prepay volume at a discount, and provisioned throughput reserves capacity for steadier cost.

Sales call required

Mixed (some tiers require a call)

Free / trial

Free trial of the Databricks platform, with credits that Databricks sets after the account is created

Lowest paid plan

Pay as you go on Databricks Units (DBUs), billed per second at published rates that vary by cloud and product

Commercial notes

The agent layer of the Databricks Data Intelligence Platform, sold under the Agent Bricks name, so pricing follows the Databricks consumption model rather than a standalone agent subscription. For teams already on Databricks, data, models, governance and agents share Unity Catalog.

Key ambiguities

Total cost depends entirely on consumption across workloads and on the cloud, so a single entry price is not meaningful. Enterprise committed use discounts are negotiated and not public.

Cancellation / refund

Pay as you go accounts can cancel at any time, and usage up to the cancellation date is charged in full. Accounts not on Azure pay monthly by card.

Support SLA / resale

Support tiers follow the Databricks platform (business, enhanced, production, and mission critical), with enterprise SLAs available on committed contracts. Available through AWS, Azure, and GCP marketplaces.

Missing data

Per DBU and per token rates vary by cloud, region and workload, so no single figure applies. Enterprise committed use discount levels are negotiated and not public.

Agentic Index verified 2026-09-27

Alternatives to Databricks Agent Bricks

The closest documented capability profiles to Databricks Agent Bricks among multi-agent platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.