Page history
agent-setup
managed-agents/agent-setup
History
managed-agents/agent-setup Changed · +11 / -11 lines
from line 14
## Agent configuration fields -| Field | Description | -| ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `name` | Required. A human-readable name for the agent. | -| `model` | Required. The Claude [model](https://platform.claude.com/docs/en/about-claude/models/overview) that powers the agent. Accepts a model ID string or an object, for example `{"id": "claude-opus-5"}`. Claude 4.5 and later models are supported. The object form also accepts `speed`, `effort`, and `inference_geo` fields; see the tips under [Create an agent](https://platform.claude.com/docs/en/managed-agents/agent-setup#create-an-agent), [Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#effort-levels), and [Pin the inference geo](https://platform.claude.com/docs/en/managed-agents/agent-setup#pin-the-inference-geo). | -| `system` | A [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role) that defines the agent's behavior and persona. The system prompt is distinct from [user messages](https://platform.claude.com/docs/en/managed-agents/reference#event-types), which should describe the work to be done. | -| `tools` | The tools available to the agent. Combines [pre-built agent tools](https://platform.claude.com/docs/en/managed-agents/tools), [MCP tools](https://platform.claude.com/docs/en/managed-agents/mcp-connector), and [custom tools](https://platform.claude.com/docs/en/managed-agents/tools#custom-tools). | -| `mcp_servers` | [MCP servers](https://platform.claude.com/docs/en/managed-agents/mcp-connector) that provide standardized third-party capabilities. | -| `skills` | [Skills](https://platform.claude.com/docs/en/managed-agents/skills) that supply domain-specific context with progressive disclosure. | -| `multiagent` | A coordinator declaration listing the agents this agent can delegate to. See [Multiagent orchestration](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration). | -| `description` | A description of what the agent does. | -| `metadata` | Arbitrary key-value pairs for your own tracking. | +| Field | Description | +| ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `name` | Required. A human-readable name for the agent. | +| `model` | Required. The Claude [model](https://platform.claude.com/docs/en/models/overview) that powers the agent. Accepts a model ID string or an object, for example `{"id": "claude-opus-5"}`. Claude 4.5 and later models are supported. The object form also accepts `speed`, `effort`, and `inference_geo` fields; see the tips under [Create an agent](https://platform.claude.com/docs/en/managed-agents/agent-setup#create-an-agent), [Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#effort-levels), and [Pin the inference geo](https://platform.claude.com/docs/en/managed-agents/agent-setup#pin-the-inference-geo). | +| `system` | A [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role) that defines the agent's behavior and persona. The system prompt is distinct from [user messages](https://platform.claude.com/docs/en/managed-agents/reference#event-types), which should describe the work to be done. | +| `tools` | The tools available to the agent. Combines [pre-built agent tools](https://platform.claude.com/docs/en/managed-agents/tools), [MCP tools](https://platform.claude.com/docs/en/managed-agents/mcp-connector), and [custom tools](https://platform.claude.com/docs/en/managed-agents/tools#custom-tools). | +| `mcp_servers` | [MCP servers](https://platform.claude.com/docs/en/managed-agents/mcp-connector) that provide standardized third-party capabilities. | +| `skills` | [Skills](https://platform.claude.com/docs/en/managed-agents/skills) that supply domain-specific context with progressive disclosure. | +| `multiagent` | A coordinator declaration listing the agents this agent can delegate to. See [Multiagent orchestration](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration). | +| `description` | A description of what the agent does. | +| `metadata` | Arbitrary key-value pairs for your own tracking. | You can also override `model`, `system`, `tools`, `mcp_servers`, and `skills` for a single session without changing the agent. An `effort` level set inside a per-session `model` override isn't applied, and because the override replaces the agent's `model` object in full, a session created with a `model` override runs at the model's default effort level; to run at a specific effort level, set `effort` on the agent and don't override `model` for that session. See [Override agent configuration for a session](https://platform.claude.com/docs/en/managed-agents/sessions#override-agent-configuration-for-a-session).
managed-agents/agent-setup Changed · +51 / -26 lines
from line 52
AGENT_VERSION=$(jq -r '.version' <<< "$agent") ``` - ```bash CLI - agent=$(ant beta:agents create \ - --name "Coding Assistant" \ - --model '{id: claude-opus-5}' \ - --system "You are a helpful coding agent." \ - --tool '{type: agent_toolset_20260401}' \ - --format json) + <MultiFileExample language="cli" label="CLI"> + ```bash CLI + agent=$(ant beta:agents create --format json < coding-assistant.agent.yaml) - AGENT_ID=$(jq -r '.id' <<< "$agent") - AGENT_VERSION=$(jq -r '.version' <<< "$agent") - ``` + AGENT_ID=$(jq -r '.id' <<< "$agent") + ``` + <File filename="coding-assistant.agent.yaml"> + ```yaml + name: Coding Assistant + model: + id: claude-opus-5 + system: You are a helpful coding agent. + tools: + - type: agent_toolset_20260401 + ``` + </File> + </MultiFileExample> + ```python Python agent = client.beta.agents.create( name="Coding Assistant",
from line 228
echo "Inference geo: $(jq -r '.model.inference_geo' <<< "$agent")" ``` - ```bash CLI - agent=$(ant beta:agents create \ - --name "Geo-pinned assistant" \ - --model '{id: claude-opus-5, inference_geo: us}' \ - --system "You are a helpful assistant." \ - --format json) + <MultiFileExample language="cli" label="CLI"> + ```bash CLI + agent=$(ant beta:agents create --format json < geo-pinned.agent.yaml) - echo "Inference geo: $(jq -r '.model.inference_geo' <<< "$agent")" - ``` + echo "Inference geo: $(jq -r '.model.inference_geo' <<< "$agent")" + ``` + <File filename="geo-pinned.agent.yaml"> + ```yaml + name: Geo-pinned assistant + model: + id: claude-opus-5 + inference_geo: us + system: You are a helpful assistant. + ``` + </File> + </MultiFileExample> + ```python Python agent = client.beta.agents.create( name="Geo-pinned assistant",
from line 367
echo "New version: $(jq -r '.version' <<< "$updated_agent")" ``` - ```bash CLI - ant beta:agents update \ - --agent-id "$AGENT_ID" \ - --version "$AGENT_VERSION" \ - --system "You are a helpful coding agent. Always write tests." - ``` + <MultiFileExample language="cli" label="CLI"> + ```bash CLI + ant beta:agents update --agent-id "$AGENT_ID" < coding-assistant.agent.yaml + ``` + + <File filename="coding-assistant.agent.yaml"> + ```yaml + name: Coding Assistant + model: + id: claude-opus-5 + system: You are a helpful coding agent. Always write tests. + tools: + - type: agent_toolset_20260401 + ``` + </File> + </MultiFileExample> ```python Python updated_agent = client.beta.agents.update(
managed-agents/agent-setup First recorded · 622 lines, first recorded
## Agent configuration fields ## Create an agent ### Pin the inference geo ## Update an agent ### Update semantics ## Agent lifecycle ### List versions ### Archive an agent ## Next steps
The first capture of this source. The page was already there, and this is what it said.
---
title: Define your agent
url: https://platform.claude.com/docs/en/managed-agents/agent-setup
description: Create a reusable, versioned agent configuration.
---
An agent is a reusable, versioned configuration that defines persona and capabilities. It bundles the model, system prompt, tools, MCP servers, and skills that shape how Claude behaves during a session.
Create the agent once as a reusable resource and reference it by ID each time you [start a session](https://platform.claude.com/docs/en/managed-agents/sessions). Agents are versioned and easier to manage across many sessions.
<Note>
Managed Agents API requests require the `managed-agents-2026-04-01` beta header, except memory store endpoints, which use `agent-memory-2026-07-22` instead. The SDK sets the correct beta header automatically. See [Beta headers](https://platform.claude.com/docs/en/api/beta-headers#endpoint-specific-headers).
</Note>
## Agent configuration fields
| Field | Description |
| ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `name` | Required. A human-readable name for the agent. |
| `model` | Required. The Claude [model](https://platform.claude.com/docs/en/about-claude/models/overview) that powers the agent. Accepts a model ID string or an object, for example `{"id": "claude-opus-5"}`. Claude 4.5 and later models are supported. The object form also accepts `speed`, `effort`, and `inference_geo` fields; see the tips under [Create an agent](https://platform.claude.com/docs/en/managed-agents/agent-setup#create-an-agent), [Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#effort-levels), and [Pin the inference geo](https://platform.claude.com/docs/en/managed-agents/agent-setup#pin-the-inference-geo). |
| `system` | A [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role) that defines the agent's behavior and persona. The system prompt is distinct from [user messages](https://platform.claude.com/docs/en/managed-agents/reference#event-types), which should describe the work to be done. |
| `tools` | The tools available to the agent. Combines [pre-built agent tools](https://platform.claude.com/docs/en/managed-agents/tools), [MCP tools](https://platform.claude.com/docs/en/managed-agents/mcp-connector), and [custom tools](https://platform.claude.com/docs/en/managed-agents/tools#custom-tools). |
| `mcp_servers` | [MCP servers](https://platform.claude.com/docs/en/managed-agents/mcp-connector) that provide standardized third-party capabilities. |
| `skills` | [Skills](https://platform.claude.com/docs/en/managed-agents/skills) that supply domain-specific context with progressive disclosure. |
| `multiagent` | A coordinator declaration listing the agents this agent can delegate to. See [Multiagent orchestration](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration). |
| `description` | A description of what the agent does. |
| `metadata` | Arbitrary key-value pairs for your own tracking. |
You can also override `model`, `system`, `tools`, `mcp_servers`, and `skills` for a single session without changing the agent. An `effort` level set inside a per-session `model` override isn't applied, and because the override replaces the agent's `model` object in full, a session created with a `model` override runs at the model's default effort level; to run at a specific effort level, set `effort` on the agent and don't override `model` for that session. See [Override agent configuration for a session](https://platform.claude.com/docs/en/managed-agents/sessions#override-agent-configuration-for-a-session).
## Create an agent
The following example defines a coding agent that uses Claude Opus 5 with access to the pre-built agent toolset. The toolset lets the agent write code, read files, search the web, and more. See the [agent tools reference](https://platform.claude.com/docs/en/managed-agents/tools) for the full list of supported tools.
The examples use curl, the `ant` CLI, or one of the SDKs. If you haven't set one up, the [quickstart](https://platform.claude.com/docs/en/managed-agents/quickstart#install-the-cli) covers installation and client setup.
<CodeGroup defaultLanguage="CLI">
```bash cURL
agent=$(curl -fsSL https://api.anthropic.com/v1/agents \
-H "x-api-key: $ANTHROPIC_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "anthropic-beta: managed-agents-2026-04-01" \
-H "content-type: application/json" \
-d '{
"name": "Coding Assistant",
"model": "claude-opus-5",
"system": "You are a helpful coding agent.",
"tools": [{"type": "agent_toolset_20260401"}]
}')
AGENT_ID=$(jq -r '.id' <<< "$agent")
AGENT_VERSION=$(jq -r '.version' <<< "$agent")
```
```bash CLI
agent=$(ant beta:agents create \
--name "Coding Assistant" \
--model '{id: claude-opus-5}' \
--system "You are a helpful coding agent." \
--tool '{type: agent_toolset_20260401}' \
--format json)
AGENT_ID=$(jq -r '.id' <<< "$agent")
AGENT_VERSION=$(jq -r '.version' <<< "$agent")
```
```python Python
agent = client.beta.agents.create(
name="Coding Assistant",
model="claude-opus-5",
system="You are a helpful coding agent.",
tools=[
{"type": "agent_toolset_20260401"},
],
)
```
```typescript TypeScript
const agent = await client.beta.agents.create({
name: "Coding Assistant",
model: "claude-opus-5",
system: "You are a helpful coding agent.",
tools: [{ type: "agent_toolset_20260401" }],
});
```
```csharp C#
var agent = await client.Beta.Agents.Create(new()
{
Name = "Coding Assistant",
Model = BetaManagedAgentsModel.ClaudeOpus5,
System = "You are a helpful coding agent.",
Tools =
[
new BetaManagedAgentsAgentToolset20260401Params
{
Type = "agent_toolset_20260401",
},
],
});
```
```go Go
agent, err := client.Beta.Agents.New(ctx, anthropic.BetaAgentNewParams{
Name: "Coding Assistant",
Model: anthropic.BetaManagedAgentsModelConfigParams{
ID: anthropic.BetaManagedAgentsModelClaudeOpus5,
},
System: anthropic.String("You are a helpful coding agent."),
Tools: []anthropic.BetaAgentNewParamsToolUnion{{
OfAgentToolset20260401: &anthropic.BetaManagedAgentsAgentToolset20260401Params{
Type: anthropic.BetaManagedAgentsAgentToolset20260401ParamsTypeAgentToolset20260401,
},
}},
})
if err != nil {
panic(err)
}
```
```java Java
var agent = client.beta().agents().create(
AgentCreateParams.builder()
.name("Coding Assistant")
.model(BetaManagedAgentsModel.CLAUDE_OPUS_5)
.system("You are a helpful coding agent.")
.addTool(
BetaManagedAgentsAgentToolset20260401Params.builder()
.type(BetaManagedAgentsAgentToolset20260401Params.Type.AGENT_TOOLSET_20260401)
.build()
)
.build()
);
```
```php PHP
$agent = $client->beta->agents->create(
name: 'Coding Assistant',
model: 'claude-opus-5',
system: 'You are a helpful coding agent.',
tools: [
BetaManagedAgentsAgentToolset20260401Params::with(
type: 'agent_toolset_20260401',
),
],
);
```
```ruby Ruby
agent = client.beta.agents.create(
name: "Coding Assistant",
model: "claude-opus-5",
system_: "You are a helpful coding agent.",
tools: [{type: "agent_toolset_20260401"}]
)
```
</CodeGroup>
The response echoes your configuration and adds `id`, `type`, `version`, `created_at`, `updated_at`, and `archived_at` fields, and fills in `model` fields you omit, such as `effort`, with their defaults. The `version` starts at 1 and increments each time an update changes the agent.
```json
{
"id": "agent_01HqR2k7vXbZ9mNpL3wYcT8f",
"type": "agent",
"name": "Coding Assistant",
"model": {
"id": "claude-opus-5",
"effort": { "type": "high" },
"speed": "standard"
},
"system": "You are a helpful coding agent.",
"description": null,
"tools": [
{
"type": "agent_toolset_20260401",
"default_config": {
"permission_policy": { "type": "always_allow" }
}
}
],
"skills": [],
"mcp_servers": [],
"multiagent": null,
"metadata": {},
"version": 1,
"created_at": "2026-04-03T18:24:10.412Z",
"updated_at": "2026-04-03T18:24:10.412Z",
"archived_at": null
}
```
The `default_config` on the toolset shows its default [permission policy](https://platform.claude.com/docs/en/managed-agents/permission-policies), `always_allow`, which applies unless you configure one.
<Tip>
To use Claude Opus 5 or Claude Opus 4.8 with [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode), pass `model` as an object, for example: `{"id": "claude-opus-5", "speed": "fast"}`. See the fast mode page's [supported models](https://platform.claude.com/docs/en/build-with-claude/fast-mode#supported-models).
</Tip>
<Tip>
To set the model's effort level, pass `model` as an object, for example: `{"id": "claude-opus-5", "effort": "high"}`. The `effort` field accepts a level string (`low`, `medium`, `high`, `xhigh`, or `max`) or an object such as `{"type": "high"}`. See [Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort#effort-levels) for what each level does.
</Tip>
### Pin the inference geo
Like `speed` and `effort`, `inference_geo` is set through the object form of `model`: pass `model` as an object and set `inference_geo` alongside `id`. The field accepts `"us"` or `"global"`. When it's unset, each model request follows the workspace's default inference geo at the time it's served. See [Data residency](https://platform.claude.com/docs/en/manage-claude/data-residency) for the workspace-level geo controls and pricing.
The following example pins an agent to US inference and prints the `inference_geo` value echoed in the response's `model` object:
<CodeGroup defaultLanguage="CLI">
```bash cURL
agent=$(curl -fsSL https://api.anthropic.com/v1/agents \
-H "x-api-key: $ANTHROPIC_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "anthropic-beta: managed-agents-2026-04-01" \
-H "content-type: application/json" \
-d '{
"name": "Geo-pinned assistant",
"model": {"id": "claude-opus-5", "inference_geo": "us"},
"system": "You are a helpful assistant."
}')
echo "Inference geo: $(jq -r '.model.inference_geo' <<< "$agent")"
```
```bash CLI
agent=$(ant beta:agents create \
--name "Geo-pinned assistant" \
--model '{id: claude-opus-5, inference_geo: us}' \
--system "You are a helpful assistant." \
--format json)
echo "Inference geo: $(jq -r '.model.inference_geo' <<< "$agent")"
```
```python Python
agent = client.beta.agents.create(
name="Geo-pinned assistant",
model={
"id": "claude-opus-5",
"inference_geo": "us",
},
system="You are a helpful assistant.",
)
print(f"Inference geo: {agent.model.inference_geo}")
```
```typescript TypeScript
const agent = await client.beta.agents.create({
name: "Geo-pinned assistant",
model: { id: "claude-opus-5", inference_geo: "us" },
system: "You are a helpful assistant.",
});
console.log(`Inference geo: ${agent.model.inference_geo}`);
```
```csharp C#
var agent = await client.Beta.Agents.Create(new()
{
Name = "Geo-pinned assistant",
Model = new BetaManagedAgentsModelConfigParams
{
ID = BetaManagedAgentsModel.ClaudeOpus5,
InferenceGeo = "us",
},
System = "You are a helpful assistant.",
});
Console.WriteLine($"Inference geo: {agent.Model.InferenceGeo}");
```
```go Go
agent, err := client.Beta.Agents.New(ctx, anthropic.BetaAgentNewParams{
Name: "Geo-pinned assistant",
Model: anthropic.BetaManagedAgentsModelConfigParams{
ID: anthropic.BetaManagedAgentsModelClaudeOpus5,
InferenceGeo: anthropic.String("us"),
},
System: anthropic.String("You are a helpful assistant."),
})
if err != nil {
panic(err)
}
fmt.Printf("Inference geo: %s\n", agent.Model.InferenceGeo)
```
```java Java
var agent = client.beta().agents().create(
AgentCreateParams.builder()
.name("Geo-pinned assistant")
.model(
BetaManagedAgentsModelConfigParams.builder()
.id(BetaManagedAgentsModel.CLAUDE_OPUS_5)
.inferenceGeo("us")
.build()
)
.system("You are a helpful assistant.")
.build()
);
Cut at 300 lines.