List templates

Returns the seven canonical studio functions and the shared, versioned role templates that ventures reuse.

GET /v1/agent/roster/templates

Agent → · All API references → · Get started →

Address	`https://api.hanzo.ai/v1/agent/roster/templates`
Method	`GET`
Operation	`get_agent_roster_templates`
Auth	`Authorization: Bearer $HANZO_API_KEY`

Returns the seven canonical studio functions and the shared, versioned role templates that ventures reuse.

Request

GET /v1/agent/roster/templates takes no parameters and no body — the credential is the whole request.

Response

Status	Body	Meaning
`200`	agent.rosterTemplatesOut	ok
`default`	problem-details	refused

200 body — 22 fields.

Field	In	Type	Always	Description
`functions`	body	agent.StudioFunction[]	—	Functions are the seven canonical studio functions.
`functions[].defaultOutput`	body	string	—	DefaultOutput describes the required deliverable structure and citation standard.
`functions[].defaultTools`	body	string[]	—	DefaultTools lists the MCP tool names granted by default to specialists in this function.
`functions[].duties`	body	string	—	Duties states the core responsibilities and operating boundaries of the function.
`functions[].expertise`	body	string	—	Expertise summarizes the domain specialization covered by roles in this function.
`functions[].id`	body	string	—	ID is the stable slug identifying the studio function (e.g. "regulatory-clinical").
`functions[].title`	body	string	—	Title is the human-readable name of the studio function.
`templates`	body	agent.RoleTemplate[]	—	Templates are the versioned role templates (lead plus the seven specialist functions).
`templates[].cap_micro_usd`	body	integer (int64)	—	CapMicroUSD is the default period budget cap in integer micro-USD.
`templates[].expertise`	body	string	—	Expertise is the one-line catalog description explaining when another agent or lead should delegate to this role.
`templates[].function`	body	string	—	Function is the studio function this role belongs to ("lead" or one of the seven studio functions).
`templates[].id`	body	string	—	ID is the stable template identifier (e.g. "venture-lead" or "specialist-regulatory-clinical").
`templates[].instructions`	body	string	—	Instructions is the system prompt governing how the role gathers evidence, cites sources, and flags unsupported claims.
`templates[].manager`	body	string	—	Manager is the default parent role handle this role reports to; empty for the venture lead.
`templates[].max_task_micro_usd`	body	integer (int64)	—	MaxTaskMicroUSD is the default single-run ceiling in integer micro-USD.
`templates[].output`	body	string	—	Output specifies the structured deliverable format expected from this role.
`templates[].period`	body	string	—	Period is the budget reset window: day, week, or month.
`templates[].sources`	body	string[]	—	Sources lists the authorized evidence and knowledge sources for this role.
`templates[].title`	body	string	—	Title is the human-readable role title.
`templates[].tools`	body	string[]	—	Tools lists the MCP tool names this role is allowed to invoke.
`templates[].version`	body	string	—	Version is the explicit template revision string, preserved when a venture enrolls the role.
`version`	body	string	—	Version is the current studio template catalog version string.

Failure carries the platform error shape — see Errors.

Examples

CLI

SDK

HTTP

MCP

hanzo agent roster templates

.ts

.py

.go

.rs

.java

import { Configuration, AgentApi } from 'hanzoai';

const api = new AgentApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.getAgentRosterTemplates();

from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import AgentApi

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = AgentApi(client).get_agent_roster_templates()

cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)

resp, _, err := client.AgentAPI.GetAgentRosterTemplates(context.Background()).Execute()
if err != nil {
	return err
}

use hanzo_client::apis::{configuration::Configuration, agent_api};

let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();

let result = agent_api::get_agent_roster_templates(&cfg, Default::default()).await?;

import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.AgentApi;

ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));

var result = new AgentApi(client).getAgentRosterTemplates();

The method above is the one at the current release of the document. [email protected] (npm) and [email protected] (PyPI) were generated from an earlier release, where this operation carried a different id, so it spells the method differently — regenerating the clients is what makes the two agree. SDKs →

curl https://api.hanzo.ai/v1/agent/roster/templates \
  -H "Authorization: Bearer $HANZO_API_KEY"

MCP reaches agent through the agent tool, which names its 51 operations with its own verbs — this one among them, under a name only MCP declares. describe explains any of them:

curl -X POST https://api.hanzo.ai/v1/mcp \
  -H "Content-Type: application/json" \
  -d '{
       "jsonrpc": "2.0",
       "id": 1,
       "method": "tools/call",
       "params": {
         "name": "describe",
         "arguments": {
           "op": "list_agents"
         }
       }
     }'

Agent API · All Hanzo APIs · Interactive reference

Was this page useful?

Broken link or missing step? Drop it in #docs on Discord or open a PR.

PreviousList proposals NextList runs — GET /v1/agent/runs