Agent Bricks

Agent Bricks are pre-built AI tiles in Databricks that provide conversational interfaces. This skill covers Knowledge Assistants and Supervisor Agents.

Brick	Purpose	This Skill
Knowledge Assistant (KA)	Document Q&A using RAG on PDFs/text in Volumes	✓
Supervisor Agent	Orchestrates multiple agents (KA, endpoints, UC functions, MCP)	✓

Agent Bricks是Databricks中提供对话界面的预制AI组件。本技能涵盖Knowledge Assistant和Supervisor Agent。

组件	用途	本技能覆盖
Knowledge Assistant (KA)	基于Volumes中的PDF/文本，使用RAG实现文档问答	✓
Supervisor Agent	编排多个Agent（KA、端点、UC函数、MCP）	✓

Knowledge Assistant

bash

undefined

bash

undefined

Find volumes

databricks volumes list CATALOG SCHEMA databricks experimental aitools tools query --warehouse WH "LIST '/Volumes/catalog/schema/volume/'"

Create KA

databricks knowledge-assistants create-knowledge-assistant "Name" "Description"

Add knowledge source. With --json, pass ONLY the PARENT as a positional arg

and put display_name / description / source_type / the source body (files|index|file_table)

inside the JSON. Mixing positional DISPLAY_NAME/DESCRIPTION/SOURCE_TYPE with --json errors.

databricks knowledge-assistants create-knowledge-source
"knowledge-assistants/{ka_id}"
--json '{ "display_name": "Docs", "description": "Documentation files", "source_type": "files", "files": {"path": "/Volumes/catalog/schema/volume/"} }'

Sync and check status

databricks knowledge-assistants sync-knowledge-sources "knowledge-assistants/{ka_id}" databricks knowledge-assistants get-knowledge-assistant "knowledge-assistants/{ka_id}"

List/manage

databricks knowledge-assistants list-knowledge-assistants databricks knowledge-assistants delete-knowledge-assistant "knowledge-assistants/{ka_id}" # destructive & irreversible — confirm the id first


**Source types:** `files` (Volume path) or `index` (Vector Search: `index.index_name`, `index.text_col`, `index.doc_uri_col`)

**Status:** `CREATING` (2-5 min) → `ONLINE` → `OFFLINE`

---

databricks knowledge-assistants list-knowledge-assistants databricks knowledge-assistants delete-knowledge-assistant "knowledge-assistants/{ka_id}" # destructive & irreversible — confirm the id first


**数据源类型：** `files`（Volume路径）或 `index`（向量检索：`index.index_name`, `index.text_col`, `index.doc_uri_col`）

**状态：** `CREATING`（2-5分钟）→ `ONLINE` → `OFFLINE`

---

Supervisor Agent

Native CLI:

databricks supervisor-agents

(Beta, requires CLI ≥ v1.0.0). Resource paths look like

supervisor-agents/{id}

— every command takes either that full path or a

PARENT

of that shape.

list-supervisor-agents

and

list-examples

/

list-tools

return bare JSON arrays.

bash

undefined

原生CLI：

databricks supervisor-agents

（Beta版本，要求CLI版本≥v1.0.0）。资源路径格式为

supervisor-agents/{id}

—— 所有命令都需传入完整路径或该格式的

PARENT

参数。

list-supervisor-agents

、

list-examples

/

list-tools

返回纯JSON数组。

bash

undefined

Create the supervisor agent (display name positional, description/instructions as flags)

databricks supervisor-agents create-supervisor-agent "My Supervisor"
--description "Routes queries to specialized agents"
--instructions "Route data questions to analyst, document questions to docs_agent."

→ returns {name: "supervisor-agents/<uuid>", endpoint_name: "mas-<short>-endpoint", ...}

List / get / find by name

databricks supervisor-agents list-supervisor-agents databricks supervisor-agents get-supervisor-agent supervisor-agents/<id> databricks supervisor-agents list-supervisor-agents | jq '.[] | select(.display_name == "My Supervisor")'

Update — UPDATE_MASK + new DISPLAY_NAME are positional; description/instructions optional flags

databricks supervisor-agents update-supervisor-agent supervisor-agents/<id>
"display_name,description,instructions" "My Supervisor (v2)"
--description "..." --instructions "..."

Delete (destructive & irreversible — confirm the id first)

databricks supervisor-agents delete-supervisor-agent supervisor-agents/<id>

undefined

databricks supervisor-agents delete-supervisor-agent supervisor-agents/<id>

undefined

Tools (the agents the supervisor routes to)

工具（Supervisor路由的目标Agent）

Each tool wires the supervisor to a downstream resource.

tool_type

lives in

--json

(the CLI rejects it as a positional when

--json

is used). Each type has a type-specific block (

genie_space

,

knowledge_assistant

, etc.) whose identifier field differs by type — see the table below.

bash

undefined

每个工具用于将Supervisor连接到下游资源。

tool_type

需放在

--json

参数中（当使用

--json

时，CLI不接受其作为位置参数）。每种类型都有特定类型的配置块（

genie_space

、

knowledge_assistant

等），其标识符字段因类型而异——见下表。

bash

undefined

Attach a Genie space — find its space_id with

databricks genie list-spaces

Attach a Genie space — find its space_id with

databricks genie list-spaces

databricks supervisor-agents create-tool supervisor-agents/<id> analyst --json '{ "tool_type": "genie_space", "description": "SQL analytics on the analytics warehouse", "genie_space": {"id": "<genie_space_id>"} }'

Attach a Knowledge Assistant — find ka_id with

databricks knowledge-assistants list-knowledge-assistants

Attach a Knowledge Assistant — find ka_id with

databricks knowledge-assistants list-knowledge-assistants

databricks supervisor-agents create-tool supervisor-agents/<id> docs_agent --json '{ "tool_type": "knowledge_assistant", "description": "Answers from product documentation", "knowledge_assistant": {"knowledge_assistant_id": "<ka_id>"} }'

List / get / delete tools

databricks supervisor-agents list-tools supervisor-agents/<id> databricks supervisor-agents get-tool supervisor-agents/<id>/tools/<tool_id> databricks supervisor-agents delete-tool supervisor-agents/<id>/tools/<tool_id>


**Tool types** (`tool_type` value → type-specific block):

| `tool_type` | Block | Use for |
|---|---|---|
| `genie_space` | `{"id": "<space_id>"}` | Natural language → SQL via Genie |
| `knowledge_assistant` | `{"knowledge_assistant_id": "<ka_id>"}` | Document Q&A via a KA |
| `uc_function` | `{"name": "catalog.schema.func"}` | UC SQL/Python function |
| `uc_connection` | `{"name": "<connection_name>"}` | External MCP server via UC HTTP Connection |
| `volume` | `{"name": "<full_volume_name>"}` | UC Volume browsing |
| `app` | `{"name": "<app_name>"}` | Databricks App |
| Other types (`serving_endpoint`, `lakeview_dashboard`, `supervisor_agent`, `uc_table`, `vector_search_index`, `catalog`, `schema`, `web_search`) | Block name and field shape vary | Run `databricks supervisor-agents create-tool --help` and probe — these were not verified end-to-end here. |

databricks supervisor-agents list-tools supervisor-agents/<id> databricks supervisor-agents get-tool supervisor-agents/<id>/tools/<tool_id> databricks supervisor-agents delete-tool supervisor-agents/<id>/tools/<tool_id>


**工具类型**（`tool_type`值 → 对应特定配置块）：

| `tool_type` | 配置块 | 适用场景 |
|---|---|---|
| `genie_space` | `{"id": "<space_id>"}` | 通过Genie实现自然语言转SQL |
| `knowledge_assistant` | `{"knowledge_assistant_id": "<ka_id>"}` | 通过KA实现文档问答 |
| `uc_function` | `{"name": "catalog.schema.func"}` | UC SQL/Python函数 |
| `uc_connection` | `{"name": "<connection_name>"}` | 通过UC HTTP连接对接外部MCP服务器 |
| `volume` | `{"name": "<full_volume_name>"}` | UC Volume浏览 |
| `app` | `{"name": "<app_name>"}` | Databricks应用 |
| 其他类型（`serving_endpoint`, `lakeview_dashboard`, `supervisor_agent`, `uc_table`, `vector_search_index`, `catalog`, `schema`, `web_search`） | 配置块名称和字段格式各不相同 | 运行`databricks supervisor-agents create-tool --help`查看详情——本文未对这些类型进行端到端验证。 |

Examples (training the supervisor)

示例（训练Supervisor）

Examples must use

--json

— the positional

GUIDELINES

arg doesn't accept any encoding because guidelines is a

repeated string

.

bash

databricks supervisor-agents create-example supervisor-agents/<id> --json '{
    "question": "What were Q4 revenue numbers?",
    "guidelines": ["Route to analyst Genie space", "Always group by region"]
}'

databricks supervisor-agents list-examples supervisor-agents/<id>
databricks supervisor-agents get-example supervisor-agents/<id>/examples/<ex_id>
databricks supervisor-agents delete-example supervisor-agents/<id>/examples/<ex_id>

Endpoint readiness: after

create-supervisor-agent

, the serving endpoint takes up to ~10 minutes to come online before it can answer queries.

get-supervisor-agent

returns the endpoint name immediately, but querying it is gated on the endpoint's own readiness — check via

databricks serving-endpoints get <endpoint_name>

.

示例必须使用

--json

参数——位置参数

GUIDELINES

不接受任何编码，因为guidelines是

repeated string

类型。

bash

databricks supervisor-agents create-example supervisor-agents/<id> --json '{
    "question": "What were Q4 revenue numbers?",
    "guidelines": ["Route to analyst Genie space", "Always group by region"]
}'

databricks supervisor-agents list-examples supervisor-agents/<id>
databricks supervisor-agents get-example supervisor-agents/<id>/examples/<ex_id>
databricks supervisor-agents delete-example supervisor-agents/<id>/examples/<ex_id>

端点就绪状态： 创建

supervisor-agent

后，服务端点需要约10分钟才能上线并响应查询。

get-supervisor-agent

会立即返回端点名称，但查询需等待端点就绪——可通过

databricks serving-endpoints get <endpoint_name>

检查状态。

Reference

参考资料

Topic	File
KA source types, index, troubleshooting	references/1-knowledge-assistants.md
UC functions, MCP servers, examples	references/2-supervisor-agents.md

主题	文件
KA数据源类型、索引、故障排除	references/1-knowledge-assistants.md
UC函数、MCP服务器、示例	references/2-supervisor-agents.md

databricks-agent-bricks

Original

Translation

Agent Bricks

Agent Bricks

Knowledge Assistant

Knowledge Assistant

Find volumes

Find volumes

Create KA

Create KA

Add knowledge source. With --json, pass ONLY the PARENT as a positional arg

Add knowledge source. With --json, pass ONLY the PARENT as a positional arg

and put display_name / description / source_type / the source body (files|index|file_table)

and put display_name / description / source_type / the source body (files|index|file_table)

inside the JSON. Mixing positional DISPLAY_NAME/DESCRIPTION/SOURCE_TYPE with --json errors.

inside the JSON. Mixing positional DISPLAY_NAME/DESCRIPTION/SOURCE_TYPE with --json errors.

Sync and check status

Sync and check status

List/manage

List/manage

Supervisor Agent

Supervisor Agent

Create the supervisor agent (display name positional, description/instructions as flags)

Create the supervisor agent (display name positional, description/instructions as flags)

→ returns {name: "supervisor-agents/<uuid>", endpoint_name: "mas-<short>-endpoint", ...}

→ returns {name: "supervisor-agents/<uuid>", endpoint_name: "mas-<short>-endpoint", ...}

List / get / find by name

List / get / find by name

Update — UPDATE_MASK + new DISPLAY_NAME are positional; description/instructions optional flags

Update — UPDATE_MASK + new DISPLAY_NAME are positional; description/instructions optional flags

Delete (destructive & irreversible — confirm the id first)

Delete (destructive & irreversible — confirm the id first)

Tools (the agents the supervisor routes to)

工具（Supervisor路由的目标Agent）

Attach a Genie space — find its space_id with databricks genie list-spaces

Attach a Genie space — find its space_id with databricks genie list-spaces

Attach a Knowledge Assistant — find ka_id with databricks knowledge-assistants list-knowledge-assistants

Attach a Knowledge Assistant — find ka_id with databricks knowledge-assistants list-knowledge-assistants

List / get / delete tools

List / get / delete tools

Examples (training the supervisor)

示例（训练Supervisor）

Reference

参考资料

Attach a Genie space — find its space_id with
`databricks genie list-spaces`

Attach a Genie space — find its space_id with
`databricks genie list-spaces`

Attach a Knowledge Assistant — find ka_id with
`databricks knowledge-assistants list-knowledge-assistants`

Attach a Knowledge Assistant — find ka_id with
`databricks knowledge-assistants list-knowledge-assistants`